{"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/info-nce","entry":"info_nce","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":21,"n_papers_ran":9,"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":15,"n_samples_ran":11,"n_samples_fingerprinted":2,"n_places":23,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":6,"ran_fixture":1,"ran":4,"unverified":4},"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":"2608.12695","paper":"/paper/arxiv-2608-12695","title":"The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"muha-0/ecg-ssl-representation-learning","path":"models/losses.py","file_url":"https://github.com/muha-0/ecg-ssl-representation-learning/blob/HEAD/models/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73714c075bb607a4","mcp_get_code":{"code_sha256":"73714c075bb607a4"}},{"arxiv_id":"2604.21349","paper":"/paper/arxiv-2604-21349","title":"Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"WadiiBoulila/trust-ssl","path":"trust_ssl/models/trust_ssl.py","file_url":"https://github.com/WadiiBoulila/trust-ssl/blob/HEAD/trust_ssl/models/trust_ssl.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":"08fc69f23577e6f9","mcp_get_code":{"code_sha256":"08fc69f23577e6f9"}},{"arxiv_id":"2603.17305","paper":"/paper/arxiv-2603-17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"robinzixuan/CRAFT","path":"src/lclr/lca.py","file_url":"https://github.com/robinzixuan/CRAFT/blob/HEAD/src/lclr/lca.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a662220aa93c170","mcp_get_code":{"code_sha256":"0a662220aa93c170"}},{"arxiv_id":"2506.15201","paper":null,"title":"arXiv:2506.15201","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"JiayinXu5499/PSIC","path":"loss/clip_loss.py","file_url":"https://github.com/JiayinXu5499/PSIC/blob/HEAD/loss/clip_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2000aafe4d9609e9","mcp_get_code":{"code_sha256":"2000aafe4d9609e9"}},{"arxiv_id":"2503.07259","paper":"/paper/comodo-cross-modal-video-to-imu-distillation","title":"COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Breezelled/COMODO","path":"comodo/loss.py","file_url":"https://github.com/Breezelled/COMODO/blob/HEAD/comodo/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"814f7a78b3f4f115","mcp_get_code":{"code_sha256":"814f7a78b3f4f115"}},{"arxiv_id":"2412.16483","paper":"/paper/mol-mamba-enhancing-molecular-representation","title":"MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights","date":"2024-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xian-sh/mol-mamba","path":"models/loss_info_nce.py","file_url":"https://github.com/xian-sh/mol-mamba/blob/HEAD/models/loss_info_nce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2412.01773","paper":"/paper/ferero-a-flexible-framework-for-preference","title":"FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lisha-chen/ferero","path":"ASR/Modules/utils.py","file_url":"https://github.com/lisha-chen/ferero/blob/HEAD/ASR/Modules/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1bd8e3a222e83106","mcp_get_code":{"code_sha256":"1bd8e3a222e83106"}},{"arxiv_id":"2411.15127","paper":"/paper/primus-pretraining-imu-encoders-with","title":"PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervision","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nokia-bell-labs/pretrained-imu-encoders","path":"lib/train_modules.py","file_url":"https://github.com/nokia-bell-labs/pretrained-imu-encoders/blob/HEAD/lib/train_modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"8417d5a9e637bc8d","mcp_get_code":{"code_sha256":"8417d5a9e637bc8d"}},{"arxiv_id":"2411.09894","paper":"/paper/free-lunch-in-pathology-foundation-model-task","title":"Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hku-medai/cate","path":"src/infonce.py","file_url":"https://github.com/hku-medai/cate/blob/HEAD/src/infonce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2407.12292","paper":"/paper/any-target-can-be-offense-adversarial-example","title":"Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VL-Group/GAKer","path":"utils/nce.py","file_url":"https://github.com/VL-Group/GAKer/blob/HEAD/utils/nce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2406.14017","paper":"/paper/eager-two-stream-generative-recommender-with-1","title":"EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yewzz/EAGER","path":"EAGER/lib/HF_Model.py","file_url":"https://github.com/yewzz/EAGER/blob/HEAD/EAGER/lib/HF_Model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4a92ef31fda7e78","mcp_get_code":{"code_sha256":"b4a92ef31fda7e78"}},{"arxiv_id":"2406.04815","paper":"/paper/skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/sami","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c10063e288d48256","mcp_get_code":{"code_sha256":"c10063e288d48256"}},{"arxiv_id":"2406.04815","paper":"/paper/skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/sami","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/sami/blob/HEAD/algorithm/method_step/info_nce_loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"90286ad8300b6637","mcp_get_code":{"code_sha256":"90286ad8300b6637"}},{"arxiv_id":"2406.04815","paper":"/paper/skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/SaMI","path":"algorithm/method_step/info_nce_loss.py","file_url":"https://github.com/uoe-agents/SaMI/blob/HEAD/algorithm/method_step/info_nce_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"03e6d660e5782677","mcp_get_code":{"code_sha256":"03e6d660e5782677"}},{"arxiv_id":"2404.14064","paper":"/paper/multi-view-disentanglement-for-reinforcement","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/mvd","path":"algorithms/info_nce.py","file_url":"https://github.com/uoe-agents/mvd/blob/HEAD/algorithms/info_nce.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c105e24c6a7befa4","mcp_get_code":{"code_sha256":"c105e24c6a7befa4"}},{"arxiv_id":"2401.00368","paper":"/paper/improving-text-embeddings-with-large-language","title":"Improving Text Embeddings with Large Language Models","date":"2023-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/e5-mistral-7b-instruct","path":"loss.py","file_url":"https://github.com/kamalkraj/e5-mistral-7b-instruct/blob/HEAD/loss.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":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2310.04816","paper":"/paper/hacking-generative-models-with-differentiable","title":"Hacking Generative Models with Differentiable Network Bending","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GAldegheri/gan-bending","path":"infonce.py","file_url":"https://github.com/GAldegheri/gan-bending/blob/HEAD/infonce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2308.07026","paper":"/paper/advclip-downstream-agnostic-adversarial","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cgcl-codes/advclip","path":"utils/nce.py","file_url":"https://github.com/cgcl-codes/advclip/blob/HEAD/utils/nce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2307.16377","paper":"/paper/jotr-3d-joint-contrastive-learning-with","title":"JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xljh0520/jotr","path":"common/nets/info_nce.py","file_url":"https://github.com/xljh0520/jotr/blob/HEAD/common/nets/info_nce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"2306.10008","paper":"/paper/clip2protect-protecting-facial-privacy-using-1","title":"CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search","date":"2023-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fahadshamshad/clip2protect","path":"adversarial_optimization.py","file_url":"https://github.com/fahadshamshad/clip2protect/blob/HEAD/adversarial_optimization.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"245c8c770c4dffa4","mcp_get_code":{"code_sha256":"245c8c770c4dffa4"}},{"arxiv_id":"2207.05500","paper":"/paper/modality-aware-contrastive-instance-learning","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JustinYuu/MACIL_SD","path":"InfoNCE.py","file_url":"https://github.com/JustinYuu/MACIL_SD/blob/HEAD/InfoNCE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}},{"arxiv_id":"1807.03748","paper":"/paper/representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lee-seon-woo/tscp2_pytorch","path":"src/models/losses.py","file_url":"https://github.com/lee-seon-woo/tscp2_pytorch/blob/HEAD/src/models/losses.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4bd8a922e4fd21df","mcp_get_code":{"code_sha256":"4bd8a922e4fd21df"}},{"arxiv_id":"2025.naacl-long.457","paper":null,"title":"arXiv:2025.naacl-long.457","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"atharva-naik/CRScore","path":"src/losses/info_nce.py","file_url":"https://github.com/atharva-naik/CRScore/blob/HEAD/src/losses/info_nce.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54b175c46812e410","mcp_get_code":{"code_sha256":"54b175c46812e410"}}]}