{"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/encode-data","entry":"encode_data","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":19,"n_papers_ran":7,"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":21,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":23,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":4,"unverified":13},"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":"2602.08351","paper":"/paper/arxiv-2602-08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"princeton-nlp/LESS","path":"less/data_selection/get_training_dataset.py","file_url":"https://github.com/princeton-nlp/LESS/blob/HEAD/less/data_selection/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25035506ff07d0a3","mcp_get_code":{"code_sha256":"25035506ff07d0a3"}},{"arxiv_id":"2407.15235","paper":"/paper/tagcos-task-agnostic-gradient-clustered","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2003pro/tagcos","path":"data_selection/get_training_dataset.py","file_url":"https://github.com/2003pro/tagcos/blob/HEAD/data_selection/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25035506ff07d0a3","mcp_get_code":{"code_sha256":"25035506ff07d0a3"}},{"arxiv_id":"2404.17273","paper":"/paper/3shnet-boosting-image-sentence-retrieval-via","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xurige1995/3shnet","path":"lib/evaluation_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se.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":"56b228e2d72c6b46","mcp_get_code":{"code_sha256":"56b228e2d72c6b46"}},{"arxiv_id":"2404.17273","paper":"/paper/3shnet-boosting-image-sentence-retrieval-via","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xurige1995/3shnet","path":"lib/evaluation_rgn_seg_sp_se_cross.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se_cross.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":"a624aee24b1da924","mcp_get_code":{"code_sha256":"a624aee24b1da924"}},{"arxiv_id":"2402.04333","paper":"/paper/less-selecting-influential-data-for-targeted","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/less","path":"less/data_selection/get_training_dataset.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/data_selection/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25035506ff07d0a3","mcp_get_code":{"code_sha256":"25035506ff07d0a3"}},{"arxiv_id":"2310.17468","paper":"/paper/cross-modal-active-complementary-learning-1","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QinYang79/CRCL","path":"CRCL_NeurIPS23/evaluation.py","file_url":"https://github.com/QinYang79/CRCL/blob/HEAD/CRCL_NeurIPS23/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bdf65a1c26e5fec5","mcp_get_code":{"code_sha256":"bdf65a1c26e5fec5"}},{"arxiv_id":"2309.17368","paper":"/paper/machine-learning-for-practical-quantum-error","title":"Machine Learning for Practical Quantum Error Mitigation","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiskit-community/blackwater","path":"blackwater/library/learning/mlp.py","file_url":"https://github.com/qiskit-community/blackwater/blob/HEAD/blackwater/library/learning/mlp.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":"7addf7c43dfbba96","mcp_get_code":{"code_sha256":"7addf7c43dfbba96"}},{"arxiv_id":"2308.04380","paper":"/paper/your-negative-may-not-be-true-negative","title":"Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luminosityx/fne","path":"evaluation.py","file_url":"https://github.com/luminosityx/fne/blob/HEAD/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"e495a1237371ad97","mcp_get_code":{"code_sha256":"e495a1237371ad97"}},{"arxiv_id":"2306.08789","paper":"/paper/efficient-token-guided-image-text-retrieval","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lcfractal/tgdt","path":"evaluation.py","file_url":"https://github.com/lcfractal/tgdt/blob/HEAD/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a365ec8a05fffb9","mcp_get_code":{"code_sha256":"5a365ec8a05fffb9"}},{"arxiv_id":"2211.06550","paper":"/paper/tapas-a-toolbox-for-adversarial-privacy","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","date":"2022-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alan-turing-institute/privacy-sdg-toolbox","path":"tapas/generators/generator.py","file_url":"https://github.com/alan-turing-institute/privacy-sdg-toolbox/blob/HEAD/tapas/generators/generator.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05ca805c2ccad959","mcp_get_code":{"code_sha256":"05ca805c2ccad959"}},{"arxiv_id":"2010.03403","paper":"/paper/universal-weighting-metric-learning-for-cross-1","title":"Universal Weighting Metric Learning for Cross-Modal Matching","date":"2020-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wayne980/PolyLoss","path":"evaluation.py","file_url":"https://github.com/wayne980/PolyLoss/blob/HEAD/evaluation.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":"9fb1dc913236e6d2","mcp_get_code":{"code_sha256":"9fb1dc913236e6d2"}},{"arxiv_id":"2008.05231","paper":"/paper/fine-grained-visual-textual-alignment-for","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","date":"2020-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mesnico/TERAN","path":"evaluation.py","file_url":"https://github.com/mesnico/TERAN/blob/HEAD/evaluation.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":"e919b63bdc37e394","mcp_get_code":{"code_sha256":"e919b63bdc37e394"}},{"arxiv_id":"2007.10637","paper":"/paper/distributed-memory-based-self-supervised","title":"Distributed Associative Memory Network with Memory Refreshing Loss","date":"2020-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taewonpark/DAM","path":"preprocess.py","file_url":"https://github.com/taewonpark/DAM/blob/HEAD/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"acbb1e971209606d","mcp_get_code":{"code_sha256":"acbb1e971209606d"}},{"arxiv_id":"2004.09144","paper":"/paper/transformer-reasoning-network-for-image-text","title":"Transformer Reasoning Network for Image-Text Matching and Retrieval","date":"2020-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mesnico/TERN","path":"evaluation.py","file_url":"https://github.com/mesnico/TERN/blob/HEAD/evaluation.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":"0919fda55c323689","mcp_get_code":{"code_sha256":"0919fda55c323689"}},{"arxiv_id":"2003.03772","paper":"/paper/imram-iterative-matching-with-recurrent","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","date":"2020-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HuiChen24/IMRAM","path":"evaluation.py","file_url":"https://github.com/HuiChen24/IMRAM/blob/HEAD/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ff5ad918339d214","mcp_get_code":{"code_sha256":"7ff5ad918339d214"}},{"arxiv_id":"2002.10361","paper":"/paper/multilingual-twitter-corpus-and-baselines-for","title":"Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition","date":"2020-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shangoma/Hate_Speech","path":"preprocess.py","file_url":"https://github.com/shangoma/Hate_Speech/blob/HEAD/preprocess.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":"88d73c01b2eb5aa6","mcp_get_code":{"code_sha256":"88d73c01b2eb5aa6"}},{"arxiv_id":"1909.02701","paper":"/paper/visual-semantic-reasoning-for-image-text","title":"Visual Semantic Reasoning for Image-Text Matching","date":"2019-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KunpengLi1994/VSRN","path":"evaluation_models.py","file_url":"https://github.com/KunpengLi1994/VSRN/blob/HEAD/evaluation_models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7dca92589df7e25b","mcp_get_code":{"code_sha256":"7dca92589df7e25b"}},{"arxiv_id":"1806.10348","paper":"/paper/learning-visually-grounded-semantics-from","title":"Learning Visually-Grounded Semantics from Contrastive Adversarial Samples","date":"2018-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ExplorerFreda/VSE-C","path":"VSE_C/evaluation.py","file_url":"https://github.com/ExplorerFreda/VSE-C/blob/HEAD/VSE_C/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eef3e620d10d47b","mcp_get_code":{"code_sha256":"5eef3e620d10d47b"}},{"arxiv_id":"1803.08024","paper":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhidipbhattacharyya/srl_aware_ret","path":"evaluation.py","file_url":"https://github.com/abhidipbhattacharyya/srl_aware_ret/blob/HEAD/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1119155cc37cafa8","mcp_get_code":{"code_sha256":"1119155cc37cafa8"}},{"arxiv_id":"1803.08024","paper":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuanghuei/SCAN","path":"evaluation.py","file_url":"https://github.com/kuanghuei/SCAN/blob/HEAD/evaluation.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":"77cfc8299b5facec","mcp_get_code":{"code_sha256":"77cfc8299b5facec"}},{"arxiv_id":"1803.08024","paper":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idejie/SCAN","path":"evaluation.py","file_url":"https://github.com/idejie/SCAN/blob/HEAD/evaluation.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":"647842a3913aa59c","mcp_get_code":{"code_sha256":"647842a3913aa59c"}},{"arxiv_id":"1707.05612","paper":"/paper/vse-improving-visual-semantic-embeddings-with","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","date":"2017-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kadarakos/mulisera","path":"evaluation.py","file_url":"https://github.com/kadarakos/mulisera/blob/HEAD/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7052aa5f302958f1","mcp_get_code":{"code_sha256":"7052aa5f302958f1"}},{"arxiv_id":"1707.05612","paper":"/paper/vse-improving-visual-semantic-embeddings-with","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","date":"2017-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fartashf/vsepp","path":"evaluation.py","file_url":"https://github.com/fartashf/vsepp/blob/HEAD/evaluation.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":"abbc3bafa0111c56","mcp_get_code":{"code_sha256":"abbc3bafa0111c56"}}]}