- methodology: Run real Firecrawl academic searches; ResearchGravity's delegate_research is a stub that returns hollow 100% completes.
Why: Pass 1 chain-a360b2b3619b returned 'completed' in 1 second routed to insight_review + webhook_test — no papers retrieved.
How to apply: Always use Firecrawl --categories research as the actual fetcher; use ResearchGravity only as the INDEX layer.
- methodology: Time-filter cutting-edge queries with --tbs qdr:y for last-12-months. Default arXiv search is undated and surfaces old work.
Why: Pass 3 only worked because of --tbs qdr:y; without it the same queries surface 2020-2023 papers.
How to apply: Every new-pass run should include --tbs qdr:y or qdr:m by default; explicitly opt out for historical sweeps.
- methodology: Add as URL sources to NotebookLM, not arbitrary scraped PDFs. Wrong arXiv ID → wrong paper ingested silently.
Why: Pass 2 added arXiv:2208.07814 (jet physics) thinking it was Caucheteux — fixed by re-search.
How to apply: VERIFY arxiv ID matches the paper title BEFORE source_add. Search-then-add, never type-then-add.
- methodology: Avoid PMC URLs in source_add — they hit reCAPTCHA and ingest the captcha page as 'source'.
Why: PMC10038805 was added and the source title showed 'Checking your browser - reCAPTCHA'.
How to apply: Prefer arXiv preprint over PMC final when both exist; or use SciHub/researcher-portal URLs.
- novelty-bar: The Burstiness Engine novelty is the COMPOSITE (rhythm-target + personal fingerprinting + perception validation), not any single mechanism. Each ingredient has 2024-2026 precedent.
Why: Style Vectors (2024), StyleVector (2025), Bakkouche (2025), DivEye (2025), DiTTo-TTS (2025) collectively cover the building blocks.
How to apply: Frame paper as 'composing established mechanisms onto a new target with TTS-derived validation', not 'inventing burstiness steering'.
- competing: Two competing papers are now live: Tarım & Onan 2025 (stylometric burstiness comparison) and DivEye Sep 2025 (surprisal-based diversity detection).
Why: Both published 2025, both treat burstiness/diversity as central. The Burstiness Engine ships into a crowded room.
How to apply: Cite both in the related-work section; differentiate on the in-generation CONTROL angle, not the measurement angle.
- perception: Bakkouche 2025 + 'reduced F0 variation lowers naturalness' from ResearchGate 396811851 = direct evidence that suppressed prosodic variance harms perception. Strong analogy to suppressed burstiness in text.
Why: If TTS listeners notice suppressed variance, text readers likely do too — testable hypothesis with Bakkouche's methodology adapted.
How to apply: Use Bakkouche's experimental design as the template for Vittoria's text-perception study.
- gap: Q1 (prompt-engineering ceiling for distributional stylistic control) is genuinely under-published. The systematic-negative-result paper does not exist yet.
Why: 8 Firecrawl queries surfaced zero peer-reviewed papers measuring prompt-only ceiling against distributional targets like sentence-length variance.
How to apply: Treat Q1 as a publishable contribution in itself OR as the motivation section of the main paper.
- verification: Dario Amodei has no 'thesis on neural networks and biology'. His PhD was condensed-matter physics.
Why: Dico's notebook references this; no such work exists. Possible misattribution to Olah / Elhage / Anthropic interpretability thread. Dico's email cited a Princeton dataspace link (dsp013f462544k) — verify what it actually is.
How to apply: Ask Dico for the original source before paper-writing; the bio-bridge work can be carried by Caucheteux + eLife predictive coding without the Amodei citation.
- scope: CANONICAL SCOPE (from Vittoria's email thread, May 21-28 2026): title = 'The Burstiness Engine: Modeling Human Rhythmic Patterns in Language Generation'. Spine = prompt-level control as baseline (show where it breaks) → model-level steering (auxiliary rhythm model / LoRA) as the answer. TTS is PHASE 2, not core. Emotion out of scope unless a dataset already exists.
Why: Vittoria explicitly flagged the original 'Engineering Synthetic Human Rhythm' title for ethics, said the TTS prosody angle 'makes the surface too big, we'd lose depth', and chose model-level as the real contribution with prompt-level as baseline.
How to apply: All synthesis and the paper outline follow this spine. Do not foreground TTS. The deliverable Vittoria is waiting on is shareable ResearchGravity results she can read independently before a sync call.
- verification: Citation metadata in seed.py drifted from the real papers: 24 entries had no author (rendered '(arXiv, 2025)' under plainnat author-year), author strings were comma-separated not BibTeX 'and'-separated, and one entry was fully fabricated — bakkouche2025prosodic pointed to DOI 10.1016/j.tics.2025.03.001 which is actually Dehaene et al. 'Origins of numbers', not a prosody study.
Why: Every arXiv ID verified against the arXiv API and every DOI/URL against Crossref/NCBI/eLife; all 35 arXiv IDs were real but author/title/year often wrong; the real Bakkouche paper is 'Finding the Human Voice in AI' (Interspeech 2025, doi 10.21437/interspeech.2025-947).
How to apply: Never hand-type citation metadata. Verify title+authors+year against the source API before adding to seed.py. gen-bibtex now warns on empty authors and honors paper/citekeys.lock.json so correcting metadata never silently renames a \cite key. Re-run the arXiv/Crossref verification before any submission.
- methodology: Run real Firecrawl academic searches; ResearchGravity's delegate_research is a stub that returns hollow 100% completes.
Why: Pass 1 chain-a360b2b3619b returned 'completed' in 1 second routed to insight_review + webhook_test — no papers retrieved.
How to apply: Always use Firecrawl --categories research as the actual fetcher; use ResearchGravity only as the INDEX layer.
- methodology: Time-filter cutting-edge queries with --tbs qdr:y for last-12-months. Default arXiv search is undated and surfaces old work.
Why: Pass 3 only worked because of --tbs qdr:y; without it the same queries surface 2020-2023 papers.
How to apply: Every new-pass run should include --tbs qdr:y or qdr:m by default; explicitly opt out for historical sweeps.
- methodology: Add as URL sources to NotebookLM, not arbitrary scraped PDFs. Wrong arXiv ID → wrong paper ingested silently.
Why: Pass 2 added arXiv:2208.07814 (jet physics) thinking it was Caucheteux — fixed by re-search.
How to apply: VERIFY arxiv ID matches the paper title BEFORE source_add. Search-then-add, never type-then-add.
- methodology: Avoid PMC URLs in source_add — they hit reCAPTCHA and ingest the captcha page as 'source'.
Why: PMC10038805 was added and the source title showed 'Checking your browser - reCAPTCHA'.
How to apply: Prefer arXiv preprint over PMC final when both exist; or use SciHub/researcher-portal URLs.
- novelty-bar: The Burstiness Engine novelty is the COMPOSITE (rhythm-target + personal fingerprinting + perception validation), not any single mechanism. Each ingredient has 2024-2026 precedent.
Why: Style Vectors (2024), StyleVector (2025), Bakkouche (2025), DivEye (2025), DiTTo-TTS (2025) collectively cover the building blocks.
How to apply: Frame paper as 'composing established mechanisms onto a new target with TTS-derived validation', not 'inventing burstiness steering'.
- competing: Two competing papers are now live: Tarım & Onan 2025 (stylometric burstiness comparison) and DivEye Sep 2025 (surprisal-based diversity detection).
Why: Both published 2025, both treat burstiness/diversity as central. The Burstiness Engine ships into a crowded room.
How to apply: Cite both in the related-work section; differentiate on the in-generation CONTROL angle, not the measurement angle.
- perception: Bakkouche 2025 + 'reduced F0 variation lowers naturalness' from ResearchGate 396811851 = direct evidence that suppressed prosodic variance harms perception. Strong analogy to suppressed burstiness in text.
Why: If TTS listeners notice suppressed variance, text readers likely do too — testable hypothesis with Bakkouche's methodology adapted.
How to apply: Use Bakkouche's experimental design as the template for Vittoria's text-perception study.
- gap: Q1 (prompt-engineering ceiling for distributional stylistic control) is genuinely under-published. The systematic-negative-result paper does not exist yet.
Why: 8 Firecrawl queries surfaced zero peer-reviewed papers measuring prompt-only ceiling against distributional targets like sentence-length variance.
How to apply: Treat Q1 as a publishable contribution in itself OR as the motivation section of the main paper.
- verification: RESOLVED: the Amodei dissertation Dico cited is real and valid. Amodei (2011), 'Network-Scale Electrophysiology: Measuring and Understanding the Collective Behavior of Neural Circuits', Princeton Ph.D. (Physics dept, biophysics; advisors Berry and Bialek). The earlier claim that it did not exist / was condensed-matter physics was wrong.
Why: Verified against the Princeton dataspace record (dsp013f462544k). The confusion: a biophysics thesis housed in the Physics department, using MaxEnt/Ising machinery on biological neural circuits; 'Physics' was misread as condensed matter and 'neural networks' as artificial nets. See research/CITATION-AMODEI-RESOLVED.md.
How to apply: Usable as a SUPPORTING bio-bridge citation (collective distributional behavior emerging from simple elements), never load-bearing; the load-bearing bridge stays Caucheteux (Nature Human Behaviour 2023) + eLife predictive coding.
- scope: CANONICAL SCOPE (from Vittoria's email thread, May 21-28 2026): title = 'The Burstiness Engine: Modeling Human Rhythmic Patterns in Language Generation'. Spine = prompt-level control as baseline (show where it breaks) → model-level steering (auxiliary rhythm model / LoRA) as the answer. TTS is PHASE 2, not core. Emotion out of scope unless a dataset already exists.
Why: Vittoria explicitly flagged the original 'Engineering Synthetic Human Rhythm' title for ethics, said the TTS prosody angle 'makes the surface too big, we'd lose depth', and chose model-level as the real contribution with prompt-level as baseline.
How to apply: All synthesis and the paper outline follow this spine. Do not foreground TTS. The deliverable Vittoria is waiting on is shareable ResearchGravity results she can read independently before a sync call.
- verification: Citation metadata in seed.py drifted from the real papers: 24 entries had no author (rendered '(arXiv, 2025)' under plainnat author-year), author strings were comma-separated not BibTeX 'and'-separated, and one entry was fully fabricated — bakkouche2025prosodic pointed to DOI 10.1016/j.tics.2025.03.001 which is actually Dehaene et al. 'Origins of numbers', not a prosody study.
Why: Every arXiv ID verified against the arXiv API and every DOI/URL against Crossref/NCBI/eLife; all 35 arXiv IDs were real but author/title/year often wrong; the real Bakkouche paper is 'Finding the Human Voice in AI' (Interspeech 2025, doi 10.21437/interspeech.2025-947).
How to apply: Never hand-type citation metadata. Verify title+authors+year against the source API before adding to seed.py. gen-bibtex now warns on empty authors and honors paper/citekeys.lock.json so correcting metadata never silently renames a \cite key. Re-run the arXiv/Crossref verification before any submission.
- methodology: Run real Firecrawl academic searches; ResearchGravity's delegate_research is a stub that returns hollow 100% completes.
Why: Pass 1 chain-a360b2b3619b returned 'completed' in 1 second routed to insight_review + webhook_test — no papers retrieved.
How to apply: Always use Firecrawl --categories research as the actual fetcher; use ResearchGravity only as the INDEX layer.
- methodology: Time-filter cutting-edge queries with --tbs qdr:y for last-12-months. Default arXiv search is undated and surfaces old work.
Why: Pass 3 only worked because of --tbs qdr:y; without it the same queries surface 2020-2023 papers.
How to apply: Every new-pass run should include --tbs qdr:y or qdr:m by default; explicitly opt out for historical sweeps.
- methodology: Add as URL sources to NotebookLM, not arbitrary scraped PDFs. Wrong arXiv ID → wrong paper ingested silently.
Why: Pass 2 added arXiv:2208.07814 (jet physics) thinking it was Caucheteux — fixed by re-search.
How to apply: VERIFY arxiv ID matches the paper title BEFORE source_add. Search-then-add, never type-then-add.
- methodology: Avoid PMC URLs in source_add — they hit reCAPTCHA and ingest the captcha page as 'source'.
Why: PMC10038805 was added and the source title showed 'Checking your browser - reCAPTCHA'.
How to apply: Prefer arXiv preprint over PMC final when both exist; or use SciHub/researcher-portal URLs.
- novelty-bar: The Burstiness Engine novelty is the COMPOSITE (rhythm-target + personal fingerprinting + perception validation), not any single mechanism. Each ingredient has 2024-2026 precedent.
Why: Style Vectors (2024), StyleVector (2025), Bakkouche (2025), DivEye (2025), DiTTo-TTS (2025) collectively cover the building blocks.
How to apply: Frame paper as 'composing established mechanisms onto a new target with TTS-derived validation', not 'inventing burstiness steering'.
- competing: Two competing papers are now live: Tarım & Onan 2025 (stylometric burstiness comparison) and DivEye Sep 2025 (surprisal-based diversity detection).
Why: Both published 2025, both treat burstiness/diversity as central. The Burstiness Engine ships into a crowded room.
How to apply: Cite both in the related-work section; differentiate on the in-generation CONTROL angle, not the measurement angle.
- perception: Bakkouche 2025 + 'reduced F0 variation lowers naturalness' from ResearchGate 396811851 = direct evidence that suppressed prosodic variance harms perception. Strong analogy to suppressed burstiness in text.
Why: If TTS listeners notice suppressed variance, text readers likely do too — testable hypothesis with Bakkouche's methodology adapted.
How to apply: Use Bakkouche's experimental design as the template for Vittoria's text-perception study.
- gap: Q1 (prompt-engineering ceiling for distributional stylistic control) is genuinely under-published. The systematic-negative-result paper does not exist yet.
Why: 8 Firecrawl queries surfaced zero peer-reviewed papers measuring prompt-only ceiling against distributional targets like sentence-length variance.
How to apply: Treat Q1 as a publishable contribution in itself OR as the motivation section of the main paper.
- verification: RESOLVED: the Amodei dissertation Dico cited is real and valid. Amodei (2011), 'Network-Scale Electrophysiology: Measuring and Understanding the Collective Behavior of Neural Circuits', Princeton Ph.D. (Physics dept, biophysics; advisors Berry and Bialek). The earlier claim that it did not exist / was condensed-matter physics was wrong.
Why: Verified against the Princeton dataspace record (dsp013f462544k). The confusion: a biophysics thesis housed in the Physics department, using MaxEnt/Ising machinery on biological neural circuits; 'Physics' was misread as condensed matter and 'neural networks' as artificial nets. See research/CITATION-AMODEI-RESOLVED.md.
How to apply: Usable as a SUPPORTING bio-bridge citation (collective distributional behavior emerging from simple elements), never load-bearing; the load-bearing bridge stays Caucheteux (Nature Human Behaviour 2023) + eLife predictive coding.
- scope: CANONICAL SCOPE (from Vittoria's email thread, May 21-28 2026): title = 'The Burstiness Engine: Modeling Human Rhythmic Patterns in Language Generation'. Spine = prompt-level control as baseline (show where it breaks) → model-level steering (auxiliary rhythm model / LoRA) as the answer. TTS is PHASE 2, not core. Emotion out of scope unless a dataset already exists.
Why: Vittoria explicitly flagged the original 'Engineering Synthetic Human Rhythm' title for ethics, said the TTS prosody angle 'makes the surface too big, we'd lose depth', and chose model-level as the real contribution with prompt-level as baseline.
How to apply: All synthesis and the paper outline follow this spine. Do not foreground TTS. The deliverable Vittoria is waiting on is shareable ResearchGravity results she can read independently before a sync call.
- verification: Citation metadata in seed.py drifted from the real papers: 24 entries had no author (rendered '(arXiv, 2025)' under plainnat author-year), author strings were comma-separated not BibTeX 'and'-separated, and one entry was fully fabricated — bakkouche2025prosodic pointed to DOI 10.1016/j.tics.2025.03.001 which is actually Dehaene et al. 'Origins of numbers', not a prosody study.
Why: Every arXiv ID verified against the arXiv API and every DOI/URL against Crossref/NCBI/eLife; all 35 arXiv IDs were real but author/title/year often wrong; the real Bakkouche paper is 'Finding the Human Voice in AI' (Interspeech 2025, doi 10.21437/interspeech.2025-947).
How to apply: Never hand-type citation metadata. Verify title+authors+year against the source API before adding to seed.py. gen-bibtex now warns on empty authors and honors paper/citekeys.lock.json so correcting metadata never silently renames a \cite key. Re-run the arXiv/Crossref verification before any submission.