Originality of Heuristic Rules in RNN-based Social Media Trend Prediction

Posted on by
Academic Research
Academic Research by Dmytro Grybeniuk & Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19248846  53stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted60%○≥80% from verified, high-quality sources
[a]DOI20%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed20%○≥80% have metadata indexed
[l]Academic20%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References5 refs○Minimum 10 references required
[w]Words [REQ]2,079✓Minimum 1,000 words of article body. Current: 2,079
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19248846
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness0%○≥60% of references from 2025–2026. Current: 0%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams0○Mermaid architecture/flow diagrams. Current: 0
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (33 × 60%) + Required (4/4 × 30%) + Optional (2/7 × 10%)

This methodological note describes the novel aspects of heuristic rules introduced in the FLAI (Framework for Leveraging AI in Social Media) prediction system. Specifically, we demonstrate how the three core heuristic mechanisms — base weight initialization (bW), daily repost forecast error (DRFE), and generative weight dynamic recalibration (GW) — differ fundamentally from standard weight appr...

Show moreHide
Academic Research by Dmytro Grybeniuk & Oleh Ivchenko DOI: 10.5281/zenodo.19248846 53stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted60%○≥80% from verified, high-quality sources
[a]DOI20%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed20%○≥80% have metadata indexed
[l]Academic20%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References5 refs○Minimum 10 references required
[w]Words [REQ]2,079✓Minimum 1,000 words of article body. Current: 2,079
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19248846
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness0%○≥60% of references from 2025–2026. Current: 0%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams0○Mermaid architecture/flow diagrams. Current: 0
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (33 × 60%) + Required (4/4 × 30%) + Optional (2/7 × 10%)
Anticipatory Intel…Read More
Read more

Efficiency as Intelligence: The Resource-Normalized Score for Universal Benchmarking

Posted on by
Benchmark Research
Benchmark Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19223497  73stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted72%○≥80% from verified, high-quality sources
[a]DOI56%○≥80% have a Digital Object Identifier
[b]CrossRef6%○≥80% indexed in CrossRef
[i]Indexed78%○≥80% have metadata indexed
[l]Academic56%○≥80% from journals/conferences/preprints
[f]Free Access89%✓≥80% are freely accessible
[r]References18 refs✓Minimum 10 references required
[w]Words [REQ]2,443✓Minimum 1,000 words of article body. Current: 2,443
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19223497
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness57%○≥60% of references from 2025–2026. Current: 57%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (65 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

As large language models approach ceiling performance on standard benchmarks, the question shifts from "how smart is this model?" to "how smart is this model per unit of resource consumed?" This article proposes the UIB-Efficiency dimension — a resource-normalized intelligence score that integrates accuracy with computational cost, energy consumption, memory footprint, and inference latency. We...

Show moreHide
Benchmark Research by Oleh Ivchenko DOI: 10.5281/zenodo.19223497 73stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted72%○≥80% from verified, high-quality sources
[a]DOI56%○≥80% have a Digital Object Identifier
[b]CrossRef6%○≥80% indexed in CrossRef
[i]Indexed78%○≥80% have metadata indexed
[l]Academic56%○≥80% from journals/conferences/preprints
[f]Free Access89%✓≥80% are freely accessible
[r]References18 refs✓Minimum 10 references required
[w]Words [REQ]2,443✓Minimum 1,000 words of article body. Current: 2,443
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19223497
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness57%○≥60% of references from 2025–2026. Current: 57%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (65 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
Universal Intellig…Read More
Read more

Adoption Friction Taxonomy: Categorizing the Barriers Between AI Capability and Enterprise Deployment

Posted on by
Gap Research
Gap Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19219179  61stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted47%○≥80% from verified, high-quality sources
[a]DOI13%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed87%✓≥80% have metadata indexed
[l]Academic33%○≥80% from journals/conferences/preprints
[f]Free Access80%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]2,175✓Minimum 1,000 words of article body. Current: 2,175
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19219179
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness43%○≥60% of references from 2025–2026. Current: 43%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (45 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

The gap between what AI can do and what organizations actually deploy continues to widen in 2026. While previous articles in this series quantified the magnitude of this gap across sectors, the underlying friction mechanisms remain poorly categorized. This article introduces a four-quadrant Adoption Friction Taxonomy (AFT) that classifies eight empirically identified barrier categories along tw...

Show moreHide
Gap Research by Oleh Ivchenko DOI: 10.5281/zenodo.19219179 61stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted47%○≥80% from verified, high-quality sources
[a]DOI13%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed87%✓≥80% have metadata indexed
[l]Academic33%○≥80% from journals/conferences/preprints
[f]Free Access80%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]2,175✓Minimum 1,000 words of article body. Current: 2,175
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]10✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 10
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19219179
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness43%○≥60% of references from 2025–2026. Current: 43%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (45 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
Capability-Adoptio…Read More
Read more

Fresh Repositories Watch: Healthcare AI — Emerging Open-Source Tools Under 60 Days Old

Posted on by
Open Source Research
Open Source Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19212958  81stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted86%✓≥80% from verified, high-quality sources
[a]DOI64%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed86%✓≥80% have metadata indexed
[l]Academic71%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]2,122✓Minimum 1,000 words of article body. Current: 2,122
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]8✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 8
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19212958
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed✓✓Peer reviewed by an assigned reviewer: Iryna Ivchenko
[h]Freshness17%○≥60% of references from 2025–2026. Current: 17%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (75 × 60%) + Required (4/4 × 30%) + Optional (4/7 × 10%)

The healthcare AI open-source ecosystem is experiencing unprecedented growth in early 2026, driven by federated learning platforms, foundation models for medical imaging, and synthetic data generators that enable privacy-preserving research collaboration. This article applies the Trusted Open Source Index methodology established in our previous work to evaluate nine prominent healthcare AI repo...

Show moreHide
Open Source Research by Oleh Ivchenko DOI: 10.5281/zenodo.19212958 81stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted86%✓≥80% from verified, high-quality sources
[a]DOI64%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed86%✓≥80% have metadata indexed
[l]Academic71%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]2,122✓Minimum 1,000 words of article body. Current: 2,122
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]8✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 8
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19212958
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed✓✓Peer reviewed by an assigned reviewer: Iryna Ivchenko
[h]Freshness17%○≥60% of references from 2025–2026. Current: 17%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (75 × 60%) + Required (4/4 × 30%) + Optional (4/7 × 10%)
Trusted Open SourceRead More
Read more

Semantic Prompt Caching — Beyond Exact Match

Posted on by
Technical Research
Technical Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19211071  70stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted86%✓≥80% from verified, high-quality sources
[a]DOI7%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed86%✓≥80% have metadata indexed
[l]Academic71%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]2,418✓Minimum 1,000 words of article body. Current: 2,418
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]8✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 8
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19211071
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness33%○≥60% of references from 2025–2026. Current: 33%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (60 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

Prompt caching has emerged as a critical optimization for large language model (LLM) serving, yet production systems overwhelmingly rely on exact-match strategies that miss semantically equivalent queries. This article investigates semantic prompt caching — systems that identify and serve cached responses for semantically similar (but not identical) prompts using embedding-based similarity dete...

Show moreHide
Technical Research by Oleh Ivchenko DOI: 10.5281/zenodo.19211071 70stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted86%✓≥80% from verified, high-quality sources
[a]DOI7%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed86%✓≥80% have metadata indexed
[l]Academic71%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]2,418✓Minimum 1,000 words of article body. Current: 2,418
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]8✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 8
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19211071
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness33%○≥60% of references from 2025–2026. Current: 33%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (60 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
AI MemoryRead More
Read more

Speculative Decoding and Cache Reuse

Posted on by
Technical Research
Technical Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19210815  72stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI5%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed90%✓≥80% have metadata indexed
[l]Academic81%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]2,744✓Minimum 1,000 words of article body. Current: 2,744
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]15✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 15
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19210815
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness21%○≥60% of references from 2025–2026. Current: 21%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (63 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

Speculative decoding has emerged as a transformative inference optimization that breaks the sequential bottleneck of autoregressive generation by drafting multiple tokens in parallel and verifying them in a single forward pass. This article examines three research questions at the intersection of speculative decoding and KV cache management: how draft-then-verify architectures interact with cac...

Show moreHide
Technical Research by Oleh Ivchenko DOI: 10.5281/zenodo.19210815 72stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI5%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed90%✓≥80% have metadata indexed
[l]Academic81%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]2,744✓Minimum 1,000 words of article body. Current: 2,744
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]15✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 15
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19210815
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness21%○≥60% of references from 2025–2026. Current: 21%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (63 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
AI MemoryRead More
Read more

Social and Collaborative Intelligence as a UIB Dimension: Why Theory of Mind Remains the Hardest Benchmark

Posted on by
Benchmark Research
Benchmark Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19209792  73stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources6%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI18%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic76%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References17 refs✓Minimum 10 references required
[w]Words [REQ]2,385✓Minimum 1,000 words of article body. Current: 2,385
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]11✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 11
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19209792
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness13%○≥60% of references from 2025–2026. Current: 13%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (65 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

Current AI evaluation overwhelmingly focuses on individual cognitive tasks — reasoning, coding, mathematics — while neglecting the social and collaborative capabilities that define human intelligence in practice. This article introduces the UIB-Social dimension, a formal evaluation framework for measuring social intelligence in large language models across four sub-dimensions: Theory of Mind (T...

Show moreHide
Benchmark Research by Oleh Ivchenko DOI: 10.5281/zenodo.19209792 73stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources6%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI18%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic76%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References17 refs✓Minimum 10 references required
[w]Words [REQ]2,385✓Minimum 1,000 words of article body. Current: 2,385
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]11✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 11
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19209792
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness13%○≥60% of references from 2025–2026. Current: 13%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (65 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
Universal Intellig…Read More
Read more

Grouped-Query Attention — Cache-Efficient Architecture Design

Posted on by
Technical Research
Technical Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19209159  84stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources4%○≥80% from editorially reviewed sources
[t]Trusted92%✓≥80% from verified, high-quality sources
[a]DOI79%○≥80% have a Digital Object Identifier
[b]CrossRef4%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic83%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References24 refs✓Minimum 10 references required
[w]Words [REQ]2,591✓Minimum 1,000 words of article body. Current: 2,591
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]18✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 18
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19209159
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness36%○≥60% of references from 2025–2026. Current: 36%
[c]Data Charts5✓Original data charts from reproducible analysis (min 2). Current: 5
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (83 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

As large language models scale beyond hundreds of billions of parameters and context windows extend to millions of tokens, the key-value (KV) cache required for attention computation becomes the dominant memory bottleneck during inference. Grouped-Query Attention (GQA) addresses this by allowing multiple query heads to share fewer key-value heads, reducing cache footprint while preserving model...

Show moreHide
Technical Research by Oleh Ivchenko DOI: 10.5281/zenodo.19209159 84stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources4%○≥80% from editorially reviewed sources
[t]Trusted92%✓≥80% from verified, high-quality sources
[a]DOI79%○≥80% have a Digital Object Identifier
[b]CrossRef4%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic83%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References24 refs✓Minimum 10 references required
[w]Words [REQ]2,591✓Minimum 1,000 words of article body. Current: 2,591
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]18✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 18
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19209159
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness36%○≥60% of references from 2025–2026. Current: 36%
[c]Data Charts5✓Original data charts from reproducible analysis (min 2). Current: 5
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (83 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
AI MemoryRead More
Read more

Temporal and Planning Intelligence as a UIB Dimension: Why Horizon Length Breaks Modern Reasoning Models

Posted on by
Benchmark Research
Benchmark Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19207333  81stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI63%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic69%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References16 refs✓Minimum 10 references required
[w]Words [REQ]2,436✓Minimum 1,000 words of article body. Current: 2,436
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]9✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 9
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19207333
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness62%✓≥60% of references from 2025–2026. Current: 62%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (75 × 60%) + Required (4/4 × 30%) + Optional (4/7 × 10%)

Temporal reasoning and long-horizon planning represent perhaps the most consequential gap between current large language models and human cognitive capability. While frontier models achieve near-human performance on short planning tasks (under 15 steps), their accuracy degrades catastrophically beyond 25 planning steps — a phenomenon we term the horizon collapse. This article examines three res...

Show moreHide
Benchmark Research by Oleh Ivchenko DOI: 10.5281/zenodo.19207333 81stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI63%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed88%✓≥80% have metadata indexed
[l]Academic69%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References16 refs✓Minimum 10 references required
[w]Words [REQ]2,436✓Minimum 1,000 words of article body. Current: 2,436
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]9✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 9
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19207333
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness62%✓≥60% of references from 2025–2026. Current: 62%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (75 × 60%) + Required (4/4 × 30%) + Optional (4/7 × 10%)
Universal Intellig…Read More
Read more

Paged Attention and Virtual Memory for LLM Inference

Posted on by
Technical Research
Technical Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19203099  70stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources13%○≥80% from editorially reviewed sources
[t]Trusted73%○≥80% from verified, high-quality sources
[a]DOI27%○≥80% have a Digital Object Identifier
[b]CrossRef13%○≥80% indexed in CrossRef
[i]Indexed80%✓≥80% have metadata indexed
[l]Academic60%○≥80% from journals/conferences/preprints
[f]Free Access87%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]3,035✓Minimum 1,000 words of article body. Current: 3,035
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]9✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 9
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19203099
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness31%○≥60% of references from 2025–2026. Current: 31%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (60 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)

As large language models scale to billions of parameters and millions of context tokens, the key-value (KV) cache that stores attention states becomes the dominant memory bottleneck during inference. Traditional contiguous memory allocation for KV caches leads to severe fragmentation — wasting 40-60% of available GPU memory — and fundamentally limits serving throughput. This article investigate...

Show moreHide
Technical Research by Oleh Ivchenko DOI: 10.5281/zenodo.19203099 70stabilfr·wuedophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources13%○≥80% from editorially reviewed sources
[t]Trusted73%○≥80% from verified, high-quality sources
[a]DOI27%○≥80% have a Digital Object Identifier
[b]CrossRef13%○≥80% indexed in CrossRef
[i]Indexed80%✓≥80% have metadata indexed
[l]Academic60%○≥80% from journals/conferences/preprints
[f]Free Access87%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]3,035✓Minimum 1,000 words of article body. Current: 3,035
[u]Original [REQ]100%✓≥85% unique sentences (no padding or repeated blocks) and no leaked drafting notes. Current: 100% unique
[e]Evidence [REQ]9✓Cites at least 1 external source(s): links, DOIs or a reference list. Current: 9
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19203099
[o]ORCID✓✓Author ORCID verified for academic identity
[p]Peer Reviewed—○Peer reviewed by an assigned reviewer
[h]Freshness31%○≥60% of references from 2025–2026. Current: 31%
[c]Data Charts4✓Original data charts from reproducible analysis (min 2). Current: 4
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (60 × 60%) + Required (4/4 × 30%) + Optional (3/7 × 10%)
AI MemoryRead More
Read more