{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/apply-rope","entry":"apply_rope","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":43,"n_papers_ran":26,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":23,"n_samples_ran":12,"n_samples_fingerprinted":9,"n_places":44,"n_places_pointer_only":16,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":5,"ran_fixture":2,"ran":4,"unverified":11},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.22347","paper":"/paper/arxiv-2608-22347","title":"Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive Architecture","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"fmarrabal/miuracognitive","path":"model/transformer.py","file_url":"https://github.com/fmarrabal/miuracognitive/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d388fa934b5e3f96","mcp_get_code":{"code_sha256":"d388fa934b5e3f96"}},{"arxiv_id":"2608.18261","paper":"/paper/arxiv-2608-18261","title":"Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall A Pre-Registered Negative Result, with a Systems Measurement Study","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Shriniwas410/cacheable-by-design","path":"model.py","file_url":"https://github.com/Shriniwas410/cacheable-by-design/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07941306772c339b","mcp_get_code":{"code_sha256":"07941306772c339b"}},{"arxiv_id":"2608.07249","paper":"/paper/arxiv-2608-07249","title":"Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ericu9500/stoicheia","path":"hf_release/modeling_char_bert_joint.py","file_url":"https://github.com/ericu9500/stoicheia/blob/HEAD/hf_release/modeling_char_bert_joint.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b0a953e8c8431de","mcp_get_code":{"code_sha256":"7b0a953e8c8431de"}},{"arxiv_id":"2607.26504","paper":"/paper/arxiv-2607-26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"SeunggeunKimkr/genuine-any-order","path":"LatentMDM/model/latent_mdm.py","file_url":"https://github.com/SeunggeunKimkr/genuine-any-order/blob/HEAD/LatentMDM/model/latent_mdm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bc605409c93e760b","mcp_get_code":{"code_sha256":"bc605409c93e760b"}},{"arxiv_id":"2606.14971","paper":"/paper/arxiv-2606-14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hrtan/fastmix","path":"lit_gpt/model.py","file_url":"https://github.com/hrtan/fastmix/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2605.30965","paper":"/paper/arxiv-2605-30965","title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"black-forest-labs/flux","path":"src/flux/math.py","file_url":"https://github.com/black-forest-labs/flux/blob/HEAD/src/flux/math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3444bbcc9065f707","mcp_get_code":{"code_sha256":"3444bbcc9065f707"}},{"arxiv_id":"2605.30100","paper":"/paper/arxiv-2605-30100","title":"CHESS-WORLD-MODEL: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Benjamin-Walker/Chess-World-Model","path":"models/transformer.py","file_url":"https://github.com/Benjamin-Walker/Chess-World-Model/blob/HEAD/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"289ce4c835947e59","mcp_get_code":{"code_sha256":"289ce4c835947e59"}},{"arxiv_id":"2605.26502","paper":"/paper/arxiv-2605-26502","title":"PRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"wang-henry4/prism","path":"prism/model/prefix_material_thk_model.py","file_url":"https://github.com/wang-henry4/prism/blob/HEAD/prism/model/prefix_material_thk_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c6b2f793d0099d9","mcp_get_code":{"code_sha256":"9c6b2f793d0099d9"}},{"arxiv_id":"2605.16234","paper":"/paper/arxiv-2605-16234","title":"No Free Swap: Protocol-Dependent Layer Redundancy in Transformers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Gpgabriel25/ProtocolGapDiagnostic","path":"clean_oracle_bootstrap_ci.py","file_url":"https://github.com/Gpgabriel25/ProtocolGapDiagnostic/blob/HEAD/clean_oracle_bootstrap_ci.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1d1f71ed01bdb63e","mcp_get_code":{"code_sha256":"1d1f71ed01bdb63e"}},{"arxiv_id":"2605.15509","paper":"/paper/arxiv-2605-15509","title":"parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"xiaoyang-123-cell/ParallelCBF","path":"parallelcbf/algorithms/causal_transformer.py","file_url":"https://github.com/xiaoyang-123-cell/ParallelCBF/blob/HEAD/parallelcbf/algorithms/causal_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4fdbe3b55fbdf4b3","mcp_get_code":{"code_sha256":"4fdbe3b55fbdf4b3"}},{"arxiv_id":"2605.14200","paper":"/paper/arxiv-2605-14200","title":"How to Scale Mixture-of-Experts: From µP to the Maximally Scale-Stable Parameterization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"vankadara-lab/mssp-moe","path":"transformer-moe-experiments/model.py","file_url":"https://github.com/vankadara-lab/mssp-moe/blob/HEAD/transformer-moe-experiments/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d32ec6879733f85","mcp_get_code":{"code_sha256":"5d32ec6879733f85"}},{"arxiv_id":"2605.13989","paper":"/paper/arxiv-2605-13989","title":"VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"vectrayx/vectrayx-nano-paper","path":"training/transformer.py","file_url":"https://github.com/vectrayx/vectrayx-nano-paper/blob/HEAD/training/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e4539c0c100abce2","mcp_get_code":{"code_sha256":"e4539c0c100abce2"}},{"arxiv_id":"2605.11396","paper":"/paper/arxiv-2605-11396","title":"MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YupengSu/MuonQ","path":"src/models.py","file_url":"https://github.com/YupengSu/MuonQ/blob/HEAD/src/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"25e9d5a6a1f48f0f","mcp_get_code":{"code_sha256":"25e9d5a6a1f48f0f"}},{"arxiv_id":"2601.03955","paper":"/paper/arxiv-2601-03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Kwai-Kolors/ResTok","path":"modeling/restok.py","file_url":"https://github.com/Kwai-Kolors/ResTok/blob/HEAD/modeling/restok.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3444bbcc9065f707","mcp_get_code":{"code_sha256":"3444bbcc9065f707"}},{"arxiv_id":"2507.07101","paper":null,"title":"arXiv:2507.07101","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"martin-marek/batch-size","path":"finetuning/rope.py","file_url":"https://github.com/martin-marek/batch-size/blob/HEAD/finetuning/rope.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae9c4ad2e718b1ea","mcp_get_code":{"code_sha256":"ae9c4ad2e718b1ea"}},{"arxiv_id":"2504.11393","paper":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/prox","path":"train/lit_gpt/model.py","file_url":"https://github.com/gair-nlp/prox/blob/HEAD/train/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2503.15450","paper":"/paper/skyladder-better-and-faster-pretraining-via","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/skyladder","path":"lit_gpt/model.py","file_url":"https://github.com/sail-sg/skyladder/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2503.05631","paper":"/paper/strategy-coopetition-explains-the-emergence","title":"Strategy Coopetition Explains the Emergence and Transience of In-Context Learning","date":"2025-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"369d990a59246f7f","mcp_get_code":{"code_sha256":"369d990a59246f7f"}},{"arxiv_id":"2502.17363","paper":"/paper/kv-edit-training-free-image-editing-for","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xilluill/KV-Edit","path":"models/kv_edit.py","file_url":"https://github.com/Xilluill/KV-Edit/blob/HEAD/models/kv_edit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b46f68f6e5e0e3d","mcp_get_code":{"code_sha256":"7b46f68f6e5e0e3d"}},{"arxiv_id":"2502.04320","paper":"/paper/conceptattention-diffusion-transformers-learn","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"helblazer811/ConceptAttention","path":"concept_attention/flux/dit_block.py","file_url":"https://github.com/helblazer811/ConceptAttention/blob/HEAD/concept_attention/flux/dit_block.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f1b2506d32e33e3","mcp_get_code":{"code_sha256":"7f1b2506d32e33e3"}},{"arxiv_id":"2502.01105","paper":"/paper/layertracer-cognitive-aligned-layered-svg","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/LayerTracer","path":"library/flux_models.py","file_url":"https://github.com/showlab/LayerTracer/blob/HEAD/library/flux_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad4327d0fd3beb3a","mcp_get_code":{"code_sha256":"ad4327d0fd3beb3a"}},{"arxiv_id":"2412.07517","paper":"/paper/fireflow-fast-inversion-of-rectified-flow-for","title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"holmesshuan/fireflow","path":"src/flux/math.py","file_url":"https://github.com/holmesshuan/fireflow/blob/HEAD/src/flux/math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3444bbcc9065f707","mcp_get_code":{"code_sha256":"3444bbcc9065f707"}},{"arxiv_id":"2411.12892","paper":"/paper/selective-attention-enhancing-transformer","title":"Selective Attention: Enhancing Transformer through Principled Context Control","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umich-sota/selective_attention","path":"lit_gpt/model.py","file_url":"https://github.com/umich-sota/selective_attention/blob/HEAD/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2411.04746","paper":"/paper/taming-rectified-flow-for-inversion-and","title":"Taming Rectified Flow for Inversion and Editing","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangjiangshan0725/rf-solver-edit","path":"FLUX_Image_Edit/src/flux/math.py","file_url":"https://github.com/wangjiangshan0725/rf-solver-edit/blob/HEAD/FLUX_Image_Edit/src/flux/math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3444bbcc9065f707","mcp_get_code":{"code_sha256":"3444bbcc9065f707"}},{"arxiv_id":"2410.11190","paper":"/paper/mini-omni2-towards-open-source-gpt-4o-model","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni2","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2410.10781","paper":"/paper/when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/attention-sink","path":"lit_gpt/model.py","file_url":"https://github.com/sail-sg/attention-sink/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2410.08102","paper":"/paper/multi-agent-collaborative-data-selection-for","title":"Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beccabai/multi-agent-data-selection","path":"src/lit_gpt/model.py","file_url":"https://github.com/beccabai/multi-agent-data-selection/blob/HEAD/src/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2409.17115","paper":"/paper/programming-every-example-lifting-pre","title":"Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2409.00587","paper":"/paper/flux-that-plays-music","title":"FLUX that Plays Music","date":"2024-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/fluxmusic","path":"modules/layers.py","file_url":"https://github.com/feizc/fluxmusic/blob/HEAD/modules/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3444bbcc9065f707","mcp_get_code":{"code_sha256":"3444bbcc9065f707"}},{"arxiv_id":"2408.16725","paper":"/paper/mini-omni-language-models-can-hear-talk-while","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni/blob/HEAD/litgpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2408.03506","paper":"/paper/1-5-pints-technical-report-pretraining-in","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","date":"2024-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pints-AI/1.5-Pints","path":"lit_gpt/model.py","file_url":"https://github.com/Pints-AI/1.5-Pints/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2406.10209","paper":"/paper/be-like-a-goldfish-don-t-memorize-mitigating","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahans30/goldfish-loss","path":"lit_gpt/model.py","file_url":"https://github.com/ahans30/goldfish-loss/blob/HEAD/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2406.06046","paper":"/paper/mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/MATES","path":"src/lit_gpt/model.py","file_url":"https://github.com/cxcscmu/MATES/blob/HEAD/src/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa32c6faaa562b69","mcp_get_code":{"code_sha256":"aa32c6faaa562b69"}},{"arxiv_id":"2405.20340","paper":"/paper/motionllm-understanding-human-behaviors-from","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/MotionLLM","path":"lit_gpt/model.py","file_url":"https://github.com/IDEA-Research/MotionLLM/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2405.20340","paper":"/paper/motionllm-understanding-human-behaviors-from","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/MotionLLM","path":"lit_llama/model.py","file_url":"https://github.com/IDEA-Research/MotionLLM/blob/HEAD/lit_llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ebb19c1f412b0e2a","mcp_get_code":{"code_sha256":"ebb19c1f412b0e2a"}},{"arxiv_id":"2405.20053","paper":"/paper/would-i-lie-to-you-inference-time-alignment","title":"Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Avelina9X/direct-preference-heads","path":"src/model/layers.py","file_url":"https://github.com/Avelina9X/direct-preference-heads/blob/HEAD/src/model/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"f7c918ee79c006bf","mcp_get_code":{"code_sha256":"f7c918ee79c006bf"}},{"arxiv_id":"2404.07129","paper":"/paper/what-needs-to-go-right-for-an-induction-head","title":"What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation","date":"2024-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"369d990a59246f7f","mcp_get_code":{"code_sha256":"369d990a59246f7f"}},{"arxiv_id":"2402.05457","paper":"/paper/it-s-never-too-late-fusing-acoustic","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hypotheses-Paradise/UADF","path":"lit_llama/model.py","file_url":"https://github.com/Hypotheses-Paradise/UADF/blob/HEAD/lit_llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7137105772c52074","mcp_get_code":{"code_sha256":"7137105772c52074"}},{"arxiv_id":"2402.03563","paper":"/paper/distinguishing-the-knowable-from-the","title":"Distinguishing the Knowable from the Unknowable with Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gahdritz/llm_uncertainty","path":"lit-llama/model.py","file_url":"https://github.com/gahdritz/llm_uncertainty/blob/HEAD/lit-llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"16b3ba074f0d8074","mcp_get_code":{"code_sha256":"16b3ba074f0d8074"}},{"arxiv_id":"2401.02385","paper":"/paper/tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzhang38/tinyllama","path":"lit_gpt/model.py","file_url":"https://github.com/jzhang38/tinyllama/blob/HEAD/lit_gpt/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5728c74084e12d35","mcp_get_code":{"code_sha256":"5728c74084e12d35"}},{"arxiv_id":"2310.08581","paper":"/paper/universal-visual-decomposer-long-horizon","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zcczhang/uvd","path":"uvd/models/nn/transformer.py","file_url":"https://github.com/zcczhang/uvd/blob/HEAD/uvd/models/nn/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7137105772c52074","mcp_get_code":{"code_sha256":"7137105772c52074"}},{"arxiv_id":"2310.06434","paper":"/paper/whispering-llama-a-cross-modal-generative","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srijith-rkr/whispering-llama","path":"lit_llama/model.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7137105772c52074","mcp_get_code":{"code_sha256":"7137105772c52074"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lightning-AI/lit-llama","path":"lit_llama/model.py","file_url":"https://github.com/Lightning-AI/lit-llama/blob/HEAD/lit_llama/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7137105772c52074","mcp_get_code":{"code_sha256":"7137105772c52074"}},{"arxiv_id":"2205.05055","paper":"/paper/data-distributional-properties-drive-emergent","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","date":"2022-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aadityasingh/icl-dynamics","path":"models.py","file_url":"https://github.com/aadityasingh/icl-dynamics/blob/HEAD/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"369d990a59246f7f","mcp_get_code":{"code_sha256":"369d990a59246f7f"}}]}