{"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/get-model-and-tokenizer","entry":"get_model_and_tokenizer","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":15,"n_papers_ran":0,"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":18,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":18},"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":"2604.19052","paper":"/paper/arxiv-2604-19052","title":"Cell-Based Representation of Relational Binding in Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cl-tohoku/CBR-Subsapce","path":"script/activation_extraction.py","file_url":"https://github.com/cl-tohoku/CBR-Subsapce/blob/HEAD/script/activation_extraction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d40c60f64831192e","mcp_get_code":{"code_sha256":"d40c60f64831192e"}},{"arxiv_id":"2604.19052","paper":"/paper/arxiv-2604-19052","title":"Cell-Based Representation of Relational Binding in Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cl-tohoku/CBR-Subsapce","path":"script/activation_perturbing.py","file_url":"https://github.com/cl-tohoku/CBR-Subsapce/blob/HEAD/script/activation_perturbing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5fa86ace27601859","mcp_get_code":{"code_sha256":"5fa86ace27601859"}},{"arxiv_id":"2604.14602","paper":"/paper/arxiv-2604-14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"unitaryai/detoxify","path":"detoxify/detoxify.py","file_url":"https://github.com/unitaryai/detoxify/blob/HEAD/detoxify/detoxify.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":"12904fe5b793594c","mcp_get_code":{"code_sha256":"12904fe5b793594c"}},{"arxiv_id":"2602.15902","paper":"/paper/arxiv-2602-15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"SakanaAI/doc-to-lora","path":"src/ctx_to_lora/modeling/text_to_lora.py","file_url":"https://github.com/SakanaAI/doc-to-lora/blob/HEAD/src/ctx_to_lora/modeling/text_to_lora.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d38e50d952d93469","mcp_get_code":{"code_sha256":"d38e50d952d93469"}},{"arxiv_id":"2601.17823","paper":"/paper/arxiv-2601-17823","title":"DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pkasela/DIETA-Machine-Translation","path":"src/translate.py","file_url":"https://github.com/pkasela/DIETA-Machine-Translation/blob/HEAD/src/translate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5fbf0ad06038b772","mcp_get_code":{"code_sha256":"5fbf0ad06038b772"}},{"arxiv_id":"2601.17823","paper":"/paper/arxiv-2601-17823","title":"DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pkasela/DIETA-Machine-Translation","path":"src/translate_en_it.py","file_url":"https://github.com/pkasela/DIETA-Machine-Translation/blob/HEAD/src/translate_en_it.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f428b05792c9562a","mcp_get_code":{"code_sha256":"f428b05792c9562a"}},{"arxiv_id":"2511.13223","paper":"/paper/arxiv-2511-13223","title":"TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"zhangyx1122/TokenSqueeze","path":"utils/tools.py","file_url":"https://github.com/zhangyx1122/TokenSqueeze/blob/HEAD/utils/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"914ae020e2d944f4","mcp_get_code":{"code_sha256":"914ae020e2d944f4"}},{"arxiv_id":"2502.11877","paper":"/paper/jolt-joint-probabilistic-predictions-on","title":"JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridge-mlg/jolt","path":"hf_api.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/hf_api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"863e886e0d44db0d","mcp_get_code":{"code_sha256":"863e886e0d44db0d"}},{"arxiv_id":"2502.11877","paper":"/paper/jolt-joint-probabilistic-predictions-on","title":"JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"requeima/llm_processes","path":"llm_processes/hf_api.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/hf_api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6d5041d9ba211b14","mcp_get_code":{"code_sha256":"6d5041d9ba211b14"}},{"arxiv_id":"2406.12128","paper":"/paper/ai-news-content-farms-are-easy-to-make-and","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpucce/synthetic_llm_data","path":"src/data_generation/data_complete.py","file_url":"https://github.com/gpucce/synthetic_llm_data/blob/HEAD/src/data_generation/data_complete.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"18e76676f374297a","mcp_get_code":{"code_sha256":"18e76676f374297a"}},{"arxiv_id":"2405.16282","paper":"/paper/confidence-under-the-hood-an-investigation","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akkeshav/confidence_probability_alignment","path":"get_confidence.py","file_url":"https://github.com/akkeshav/confidence_probability_alignment/blob/HEAD/get_confidence.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6473e0d73faf9415","mcp_get_code":{"code_sha256":"6473e0d73faf9415"}},{"arxiv_id":"2402.11493","paper":"/paper/benchmarking-knowledge-boundary-for-large","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkulcwmzx/knowledge-boundary","path":"model_utils.py","file_url":"https://github.com/pkulcwmzx/knowledge-boundary/blob/HEAD/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3244f3e967f2f156","mcp_get_code":{"code_sha256":"3244f3e967f2f156"}},{"arxiv_id":"2402.10835","paper":"/paper/time-series-forecasting-with-llms","title":"Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuj666/time-series-forecasting-with-llms","path":"models/llama.py","file_url":"https://github.com/mingyuj666/time-series-forecasting-with-llms/blob/HEAD/models/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42592f351c8e9f61","mcp_get_code":{"code_sha256":"42592f351c8e9f61"}},{"arxiv_id":"2401.06532","paper":"/paper/inters-unlocking-the-power-of-large-language","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DaoD/INTERS","path":"evaluation/qdu-tasks/src/modeling.py","file_url":"https://github.com/DaoD/INTERS/blob/HEAD/evaluation/qdu-tasks/src/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5ceb4dcfea73278","mcp_get_code":{"code_sha256":"a5ceb4dcfea73278"}},{"arxiv_id":"2310.05869","paper":"/paper/hyperattention-long-context-attention-in-near","title":"HyperAttention: Long-context Attention in Near-Linear Time","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amirzandieh/HyperAttention","path":"benchmark_patch_llm.py","file_url":"https://github.com/amirzandieh/HyperAttention/blob/HEAD/benchmark_patch_llm.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":"3ddcd89b0fab00be","mcp_get_code":{"code_sha256":"3ddcd89b0fab00be"}},{"arxiv_id":"2307.09476","paper":"/paper/overthinking-the-truth-understanding-how","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dannyallover/overthinking_the_truth","path":"dev/model.py","file_url":"https://github.com/dannyallover/overthinking_the_truth/blob/HEAD/dev/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f09803076d415f74","mcp_get_code":{"code_sha256":"f09803076d415f74"}},{"arxiv_id":"2305.07759","paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vizuaraai/tiny-stories-regional","path":"translation/get_model_token.py","file_url":"https://github.com/vizuaraai/tiny-stories-regional/blob/HEAD/translation/get_model_token.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"654be48c7a17f9d2","mcp_get_code":{"code_sha256":"654be48c7a17f9d2"}},{"arxiv_id":"2210.07228","paper":"/paper/language-model-decoding-as-likelihood-utility","title":"Language Model Decoding as Likelihood-Utility Alignment","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfl-dlab/understanding-decoding","path":"detoxify/src/utils.py","file_url":"https://github.com/epfl-dlab/understanding-decoding/blob/HEAD/detoxify/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfaef4c55ff6fd63","mcp_get_code":{"code_sha256":"cfaef4c55ff6fd63"}}]}