MachineSex/paper/manuscript/refs/resolution-report.tsv
Giorgio Gilestro ab3dc10587 Restructure: descriptive tier and experiment names, paper/manuscript
- paper/pnas -> paper/manuscript (venue-neutral)
- configs/layer1 -> configs/inheritance, src/knowledge -> src/inheritance
  (imported as `inheritance`), make layer1 -> make inheritance; layer2 alias dropped
- inheritance and trained-network bundles named after the manuscript figure
  they feed (fig2_grounding_sweep, figS3_rebaselining, ...), or descriptively
  where they feed none; configs keep their `experiment:` value so parquet
  hashes are unchanged, only output.dir moves
- figure scripts, SI figure sources, notebooks, REPRODUCING.md, README and the
  SI Methods/tables updated; make clean no longer deletes tracked manifests;
  reproduce.sh hashes the s{seed}/ layouts too

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
2026-09-13 17:00:40 +01:00

9.5 KiB
Raw Permalink Blame History

11OK 10.48550/arXiv.2508.06811Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugin manuscript
22OK 10.48550/arXiv.2405.18432Unsupervised Model Tree Heritage Recoveryin manuscript
33OK 10.48550/arXiv.2402.00699PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models iin manuscript
44OK 10.48550/arXiv.2306.01708TIES-Merging: Resolving Interference When Merging Modelsin manuscript
55OK 10.1038/s42256-024-00975-8Evolutionary optimization of model merging recipescrossref (matched: Evolutionary optimization of model merging recipes)
66OK 10.48550/arXiv.2403.13257Arcee's MergeKit: A Toolkit for Merging Large Language Modelsin manuscript
77OK 10.48550/arXiv.2408.07666Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Appin manuscript
88OK 10.48550/arXiv.2503.01155Nature-Inspired Population-Based Evolution of Large Language Modin manuscript
99OK 10.48550/arXiv.2508.16204Competition and Attraction Improve Model Fusionin manuscript
1010OK 10.48550/arXiv.2501.05707Multiagent Finetuning: Self Improvement with Diverse Reasoning Cin manuscript
1111OK 10.48550/arXiv.2406.11704Nemotron-4 340B Technical Reportin manuscript
1212OK 10.48550/arXiv.2412.08905Phi-4 Technical Reportin manuscript
1313OK 10.48550/arXiv.2212.10560Self-Instruct: Aligning Language Models with Self-Generated Instin manuscript
1414OK 10.48550/arXiv.2401.05749A Shocking Amount of the Web is Machine Translated: Insights froin manuscript
1515OK 10.48550/arXiv.2403.07183Monitoring AI-Modified Content at Scale: A Case Study on the Impin manuscript
1616OK 10.48550/arXiv.2211.04325Will we run out of data? Limits of LLM scaling based on human-gein manuscript
1717OK 10.1038/s41562-023-01742-2Machine cultureverified by hand
1818OK 10.48550/arXiv.2304.03442Generative Agents: Interactive Simulacra of Human Behaviorin manuscript
1919OK 10.48550/arXiv.2402.01680Large Language Model based Multi-Agents: A Survey of Progress anin manuscript
2020OK 10.48550/arXiv.2509.10147Virtual Agent Economiesin manuscript
2121OK 10.1038/s41586-024-07566-yAI models collapse when trained on recursively generated datacrossref (matched: AI models collapse when trained on recursively generated data)
2222OK 10.1371/journal.pcbi.1002510Structural Drift: The Population Dynamics of Sequential Learningcrossref (matched: Structural Drift: The Population Dynamics of Sequential Learning)
2323OK 10.48550/arXiv.2604.08554Drift and selection in LLM text ecosystemsin manuscript
2424OK 10.48550/arXiv.2509.20101First-Extinction Law for Resampling Processesin manuscript
2525OK 10.48550/arXiv.2407.17493Model Collapse in the Self-Consuming Chain of Diffusion Finetuniin manuscript
2626OK 10.1016/s0079-7421(08)60536-8Catastrophic Interference in Connectionist Networks: The Sequentcrossref (matched: Catastrophic Interference in Connectionist Networks: The Sequential Le)
2727OK 10.1016/s1364-6613(99)01294-2Catastrophic forgetting in connectionist networkscrossref (matched: Catastrophic forgetting in connectionist networks)
2828OK 10.1016/0027-5107(64)90047-8The relation of recombination to mutational advancecrossref (matched: The relation of recombination to mutational advance)
2929OK 10.48550/arXiv.2510.16657Escaping Model Collapse via Synthetic Data Verification: Near-tein manuscript
3030OK 10.48550/arXiv.2404.01413Is Model Collapse Inevitable? Breaking the Curse of Recursion byin manuscript
3131OK 10.1093/genetics/16.2.97EVOLUTION IN MENDELIAN POPULATIONScrossref (matched: EVOLUTION IN MENDELIAN POPULATIONS)
3232OK 10.1046/j.1523-1739.1996.10061509.xThe OneMigrantperGeneration Rule in Conservation and Managemecrossref (matched: The OneMigrantperGeneration Rule in Conservation and Management)
3333HAND (pre-DOI source)[Review of] The Origin of Specieswritten by hand
3434OK 10.48550/arXiv.2411.02207Collective Model Intelligence Requires Compatible Specializationin manuscript
3535HAND (pre-DOI source)The Genetical Theory of Natural Selectionwritten by hand
3636OK 10.1086/280418Some Genetic Aspects of Sexcrossref (matched: Some Genetic Aspects of Sex)
3737OK 10.48550/arXiv.2106.09685LoRA: Low-Rank Adaptation of Large Language Modelsin manuscript
3838OK 10.1016/s0022-5193(87)80029-2Towards a general theory of adaptive walks on rugged landscapescrossref (matched: Towards a general theory of adaptive walks on rugged landscapes)
3939HAND (pre-DOI source)Coadaptation and outbreeding depressionwritten by hand
4040OK 10.1162/evco_a_00025Abandoning Objectives: Evolution Through the Search for Novelty crossref (matched: Abandoning Objectives: Evolution Through the Search for Novelty Alone)
4141OK 10.48550/arXiv.2503.05683WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editin manuscript
4242OK 10.48550/arXiv.2502.04390In Praise of Stubbornness: An Empirical Case for Cognitive-Dissoin manuscript
4343OK 10.48550/arXiv.2607.09202Interference and Retention in Continual Learningin manuscript
4444OK 10.1017/s0016672300033140A general model for the evolution of recombinationcrossref (matched: A general model for the evolution of recombination)
4545OK 10.1006/tpbi.1997.1301Deleterious Mutations, Variable Epistatic Interactions, and the crossref (matched: Deleterious Mutations, Variable Epistatic Interactions, and the Evolut)
4646OK 10.1038/nrg761Resolving the paradox of sex and recombinationcrossref (matched: Resolving the paradox of sex and recombination)
4747OK 10.1093/genetics/117.3.559Selection, Generalized Transmission and the Evolution of Modifiecrossref (matched: Selection, Generalized Transmission and the Evolution of Modifier Gene)
4848OK 10.1093/genetics/139.4.1805The population genetics of speciation: the evolution of hybrid icrossref (matched: The population genetics of speciation: the evolution of hybrid incompa)
4949OK 10.1111/j.0014-3820.2001.tb00628.xTHE EVOLUTION OF POSTZYGOTIC ISOLATION: ACCUMULATING DOBZHANSKY-crossref (matched: THE EVOLUTION OF POSTZYGOTIC ISOLATION: ACCUMULATING DOBZHANSKY-MULLER)
5050OK 10.48550/arXiv.2209.04836Git Re-Basin: Merging Models modulo Permutation Symmetriesin manuscript
5151OK 10.48550/arXiv.2606.23607Scaling Linear Mode Connectivity and Merging to Billion Parametein manuscript
5252OK 10.48550/arXiv.2410.12766The Non-Local Model Merging Problem: Permutation Symmetries and in manuscript
5353OK 10.48550/arXiv.2607.11997Are we Merging the Right Models? Impact of Expert Training Duratin manuscript
5454OK 10.48550/arXiv.2601.22285Demystifying Mergeability: Interpretable Properties to Predict Min manuscript
5555OK 10.48550/arXiv.2205.12393Fine-tuned Language Models are Continual Learnersin manuscript
5656OK 10.48550/arXiv.2403.08763Simple and Scalable Strategies to Continually Pre-train Large Lain manuscript
5757OK 10.1080/09540099550039318Catastrophic Forgetting, Rehearsal and Pseudorehearsalcrossref (matched: Catastrophic Forgetting, Rehearsal and Pseudorehearsal)
5858OK 10.48550/arXiv.1705.08690Continual Learning with Deep Generative Replayin manuscript
5959OK 10.48550/arXiv.2406.07515Beyond Model Collapse: Scaling Up with Synthesized Data Requiresin manuscript
6060OK 10.48550/arXiv.1606.04671Progressive Neural Networksin manuscript
6161OK 10.48550/arXiv.2405.09673LoRA Learns Less and Forgets Lessin manuscript
6262OK 10.1037/0033-295x.102.3.419Why there are complementary learning systems in the hippocampus crossref (matched: Why there are complementary learning systems in the hippocampus and ne)
6363OK 10.1016/j.tics.2016.05.004What Learning Systems do Intelligent Agents Need? Complementary crossref (matched: What Learning Systems do Intelligent Agents Need? Complementary Learni)
6464OK 10.48550/arXiv.1805.06370Progress &amp; Compress: A scalable framework for continual learverified by hand
6565OK 10.48550/arXiv.2212.04089Editing Models with Task Arithmeticin manuscript
6666OK 10.48550/arXiv.2407.06322MagMax: Leveraging Model Merging for Seamless Continual Learningin manuscript
6767OK 10.48550/arXiv.2407.08699Mitigating Catastrophic Forgetting in Language Transfer via Modein manuscript
6868OK 10.48550/arXiv.2412.06712How to Merge Your Multimodal Models Over Time?in manuscript
6969OK 10.48550/arXiv.1812.05159An Empirical Study of Example Forgetting during Deep Neural Netwin manuscript
7070OK 10.48550/arXiv.2211.08411Large Language Models Struggle to Learn Long-Tail Knowledgein manuscript
7171OK 10.48550/arXiv.2210.00266Long-Tailed Class Incremental Learningin manuscript
7272OK 10.48550/arXiv.2309.10105Understanding Catastrophic Forgetting in Language Models via Impin manuscript
7373OK 10.48550/arXiv.2311.03099Language Models are Super Mario: Absorbing Abilities from Homoloin manuscript
7474OK 10.48550/arXiv.2203.05482Model soups: averaging weights of multiple fine-tuned models impin manuscript
7575OK 10.48550/arXiv.2603.09463An Empirical Study and Theoretical Explanation on Task-Level Modin manuscript
7676OK 10.48550/arXiv.2506.14126From Memorization to Parameter Interference: How Overtraining Exin manuscript
7777OK 10.1145/2934662Sex as an algorithmcrossref (matched: Sex as an algorithm)
7878OK 10.48550/arXiv.2311.09807The Curious Decline of Linguistic Diversity: Training Language Min manuscript
7979OK 10.48550/arXiv.2309.05196Does Writing with Language Models Reduce Content Diversity?in manuscript
8080OK 10.1126/sciadv.adn5290Generative AI enhances individual creativity but reduces the colcrossref (matched: Generative AI enhances individual creativity but reduces the collectiv)