{"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/ngrams","entry":"ngrams","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":18,"n_papers_ran":12,"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":13,"n_samples_ran":8,"n_samples_fingerprinted":2,"n_places":18,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":4,"unverified":5},"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":"2609.02133","paper":"/paper/arxiv-2609-02133","title":"EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"18277390221/EmoStance","path":"src/latent_stance_control/evaluate_text_quality.py","file_url":"https://github.com/18277390221/EmoStance/blob/HEAD/src/latent_stance_control/evaluate_text_quality.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18f955e7c6c0319f","mcp_get_code":{"code_sha256":"18f955e7c6c0319f"}},{"arxiv_id":"2606.25152","paper":"/paper/arxiv-2606-25152","title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"kkr36/llm_detection","path":"arxiv/inference_set_rewrite/analyze_ngram_overlap.py","file_url":"https://github.com/kkr36/llm_detection/blob/HEAD/arxiv/inference_set_rewrite/analyze_ngram_overlap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"740b06b03707bbb6","mcp_get_code":{"code_sha256":"740b06b03707bbb6"}},{"arxiv_id":"2605.17932","paper":"/paper/arxiv-2605-17932","title":"Prompt Compression for Diffusion Large Language Models: An Empirical Evaluation of LLMLingua-2 and LLaDA","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"axxx129-ops/DLLM-Compression","path":"evaluation/evaluate.py","file_url":"https://github.com/axxx129-ops/DLLM-Compression/blob/HEAD/evaluation/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e8868858c2b91b7","mcp_get_code":{"code_sha256":"9e8868858c2b91b7"}},{"arxiv_id":"2508.11925","paper":"/paper/arxiv-2508-11925","title":"OPTIMIZING TOKEN CHOICE FOR CODE WATERMARK-ING: AN RL APPROACH","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"TimeLovercc/CodeTracer","path":"src/watermark/coderl.py","file_url":"https://github.com/TimeLovercc/CodeTracer/blob/HEAD/src/watermark/coderl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e8543665f0f4793","mcp_get_code":{"code_sha256":"4e8543665f0f4793"}},{"arxiv_id":"2410.24198","paper":"/paper/selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcode-project/starcoder2-self-align","path":"src/star_align/minhash_dedup.py","file_url":"https://github.com/bigcode-project/starcoder2-self-align/blob/HEAD/src/star_align/minhash_dedup.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":"a0d7edeceb109990","mcp_get_code":{"code_sha256":"a0d7edeceb109990"}},{"arxiv_id":"2406.17692","paper":"/paper/from-distributional-to-overton-pluralism","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thomlake/investigating-alignment","path":"lib/nlp.py","file_url":"https://github.com/thomlake/investigating-alignment/blob/HEAD/lib/nlp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2ed4b277c28181c","mcp_get_code":{"code_sha256":"b2ed4b277c28181c"}},{"arxiv_id":"2406.16201","paper":"/paper/blind-baselines-beat-membership-inference","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","date":"2024-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ethz-spylab/Blind-MIA","path":"greedy_selection.py","file_url":"https://github.com/ethz-spylab/Blind-MIA/blob/HEAD/greedy_selection.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a3480535a1b06aa3","mcp_get_code":{"code_sha256":"a3480535a1b06aa3"}},{"arxiv_id":"2405.15306","paper":"/paper/detikzify-synthesizing-graphics-programs-for","title":"DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"potamides/DeTikZify","path":"detikzify/evaluate/crystalbleu.py","file_url":"https://github.com/potamides/DeTikZify/blob/HEAD/detikzify/evaluate/crystalbleu.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":"fb525a5c15950a9f","mcp_get_code":{"code_sha256":"fb525a5c15950a9f"}},{"arxiv_id":"2404.11262","paper":"/paper/sampling-based-pseudo-likelihood-for","title":"Sampling-based Pseudo-Likelihood for Membership Inference Attacks","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlp-titech/samia","path":"src/eval_samia.py","file_url":"https://github.com/nlp-titech/samia/blob/HEAD/src/eval_samia.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6b2373f2ab62192c","mcp_get_code":{"code_sha256":"6b2373f2ab62192c"}},{"arxiv_id":"2402.14007","paper":"/paper/can-watermarks-survive-translation-on-the","title":"Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwhe99/x-sir","path":"src_watermark/kgw/extended_watermark_processor.py","file_url":"https://github.com/zwhe99/x-sir/blob/HEAD/src_watermark/kgw/extended_watermark_processor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"173c14a0656644b7","mcp_get_code":{"code_sha256":"173c14a0656644b7"}},{"arxiv_id":"2312.04469","paper":"/paper/on-the-learnability-of-watermarks-for","title":"On the Learnability of Watermarks for Language Models","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenchenygu/watermark-learnability","path":"watermarks/kgw/watermark_processor.py","file_url":"https://github.com/chenchenygu/watermark-learnability/blob/HEAD/watermarks/kgw/watermark_processor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"173c14a0656644b7","mcp_get_code":{"code_sha256":"173c14a0656644b7"}},{"arxiv_id":"2308.00221","paper":"/paper/advancing-beyond-identification-multi-bit","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","date":"2023-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bangawayoo/mb-lm-watermarking","path":"watermark_reliability_release/mb_watermark_processor.py","file_url":"https://github.com/bangawayoo/mb-lm-watermarking/blob/HEAD/watermark_reliability_release/mb_watermark_processor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"27868db477affd1e","mcp_get_code":{"code_sha256":"27868db477affd1e"}},{"arxiv_id":"2308.00113","paper":"/paper/three-bricks-to-consolidate-watermarks-for","title":"Three Bricks to Consolidate Watermarks for Large Language Models","date":"2023-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"173c14a0656644b7","mcp_get_code":{"code_sha256":"173c14a0656644b7"}},{"arxiv_id":"2306.17439","paper":"/paper/provable-robust-watermarking-for-ai-generated","title":"Provable Robust Watermarking for AI-Generated Text","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"173c14a0656644b7","mcp_get_code":{"code_sha256":"173c14a0656644b7"}},{"arxiv_id":"2306.04634","paper":"/paper/on-the-reliability-of-watermarks-for-large","title":"On the Reliability of Watermarks for Large Language Models","date":"2023-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jwkirchenbauer/lm-watermarking","path":"extended_watermark_processor.py","file_url":"https://github.com/jwkirchenbauer/lm-watermarking/blob/HEAD/extended_watermark_processor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"173c14a0656644b7","mcp_get_code":{"code_sha256":"173c14a0656644b7"}},{"arxiv_id":"1907.01669","paper":"/paper/multiwoz-21-multi-domain-dialogue-state","title":"MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines","date":"2019-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MoxinC/DST-SC","path":"model/Embedding.py","file_url":"https://github.com/MoxinC/DST-SC/blob/HEAD/model/Embedding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3bb03195eaecef4","mcp_get_code":{"code_sha256":"d3bb03195eaecef4"}},{"arxiv_id":"1807.03100","paper":"/paper/robust-text-to-sql-generation-with-execution","title":"Robust Text-to-SQL Generation with Execution-Guided Decoding","date":"2018-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Microsoft/PointerSQL","path":"model/util.py","file_url":"https://github.com/Microsoft/PointerSQL/blob/HEAD/model/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3bb03195eaecef4","mcp_get_code":{"code_sha256":"d3bb03195eaecef4"}},{"arxiv_id":"1806.01353","paper":"/paper/natural-language-generation-for-electronic","title":"Natural Language Generation for Electronic Health Records","date":"2018-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scotthlee/nrc","path":"metrics/text.py","file_url":"https://github.com/scotthlee/nrc/blob/HEAD/metrics/text.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":"fdc61d49aa5915e4","mcp_get_code":{"code_sha256":"fdc61d49aa5915e4"}}]}