{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TQJOMHPJVTRLI72CADVIHV2ZJZ","short_pith_number":"pith:TQJOMHPJ","canonical_record":{"source":{"id":"2006.10803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:44:13Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0b8a994bfe5e4ba14494f21848f548c620bb9552ec85fe27bc902c3f5adfc472","abstract_canon_sha256":"20634a96b781b361c6cdcb822267864eb76bcf108f27eeb2e0cf31d0d018221f"},"schema_version":"1.0"},"canonical_sha256":"9c12e61de9ace2b47f4200ea83d7594e45cb380daec90e712686b3df4556d475","source":{"kind":"arxiv","id":"2006.10803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10803","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10803v2","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10803","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"TQJOMHPJVTRL","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"TQJOMHPJVTRLI72C","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"TQJOMHPJ","created_at":"2026-07-05T01:56:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TQJOMHPJVTRLI72CADVIHV2ZJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.10803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:44:13Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0b8a994bfe5e4ba14494f21848f548c620bb9552ec85fe27bc902c3f5adfc472","abstract_canon_sha256":"20634a96b781b361c6cdcb822267864eb76bcf108f27eeb2e0cf31d0d018221f"},"schema_version":"1.0"},"canonical_sha256":"9c12e61de9ace2b47f4200ea83d7594e45cb380daec90e712686b3df4556d475","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:19.677894Z","signature_b64":"lD9y8gl84OyK2oDEhuLxxa1Y6l6PuD9utLCL+Y9kStjVqr78wApb+VlaGdaMbZA8Fxk5f0AFhCY2fMR2b1X9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c12e61de9ace2b47f4200ea83d7594e45cb380daec90e712686b3df4556d475","last_reissued_at":"2026-07-05T01:56:19.677455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:19.677455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.10803","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Vi3oJha8fVGU9NkIioHneeqYx9APUHvmwr7k7BuSSbvCLhvnDMW3gsz7J7K8F3yI+gUHouOrIY4Nt10/7pjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:20:02.484561Z"},"content_sha256":"ee9c9e2db061d088918d9b2d84be8984667195b11b8020f26533bb1bdadd0767","schema_version":"1.0","event_id":"sha256:ee9c9e2db061d088918d9b2d84be8984667195b11b8020f26533bb1bdadd0767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TQJOMHPJVTRLI72CADVIHV2ZJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lluis Castrejon, Mahmoud Assran, Michael Rabbat, Nicolas Ballas","submitted_at":"2020-06-18T18:44:13Z","abstract_excerpt":"We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on noise-contrastive estimation and neighbourhood component analysis, that aims to distinguish examples of different classes in addition to the self-supervised instance-wise pretext tasks. On ImageNet, we find that SuNCEt can be used to match the semi-supervised learning accuracy of previous contrastive approaches while using less than half the amount of pre-training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10803","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10803/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDJzHMDNLHG89qUNh5oEYixZw4bSBY1VJsmOh6Ueu25FTNHp9F6SMNWHhWifQY4HiNJ5IPi97ycbkokMm8L3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:20:02.485489Z"},"content_sha256":"4c8788a5a00abfce486706d39eb24ed550a28644f19bd6768c10b6cc1b19ed88","schema_version":"1.0","event_id":"sha256:4c8788a5a00abfce486706d39eb24ed550a28644f19bd6768c10b6cc1b19ed88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/bundle.json","state_url":"https://pith.science/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:20:02Z","links":{"resolver":"https://pith.science/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ","bundle":"https://pith.science/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/bundle.json","state":"https://pith.science/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQJOMHPJVTRLI72CADVIHV2ZJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TQJOMHPJVTRLI72CADVIHV2ZJZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"20634a96b781b361c6cdcb822267864eb76bcf108f27eeb2e0cf31d0d018221f","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:44:13Z","title_canon_sha256":"0b8a994bfe5e4ba14494f21848f548c620bb9552ec85fe27bc902c3f5adfc472"},"schema_version":"1.0","source":{"id":"2006.10803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10803","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10803v2","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10803","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"TQJOMHPJVTRL","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"TQJOMHPJVTRLI72C","created_at":"2026-07-05T01:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"TQJOMHPJ","created_at":"2026-07-05T01:56:19Z"}],"graph_snapshots":[{"event_id":"sha256:4c8788a5a00abfce486706d39eb24ed550a28644f19bd6768c10b6cc1b19ed88","target":"graph","created_at":"2026-07-05T01:56:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.10803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on noise-contrastive estimation and neighbourhood component analysis, that aims to distinguish examples of different classes in addition to the self-supervised instance-wise pretext tasks. On ImageNet, we find that SuNCEt can be used to match the semi-supervised learning accuracy of previous contrastive approaches while using less than half the amount of pre-training ","authors_text":"Lluis Castrejon, Mahmoud Assran, Michael Rabbat, Nicolas Ballas","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:44:13Z","title":"Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10803","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ee9c9e2db061d088918d9b2d84be8984667195b11b8020f26533bb1bdadd0767","target":"record","created_at":"2026-07-05T01:56:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"20634a96b781b361c6cdcb822267864eb76bcf108f27eeb2e0cf31d0d018221f","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T18:44:13Z","title_canon_sha256":"0b8a994bfe5e4ba14494f21848f548c620bb9552ec85fe27bc902c3f5adfc472"},"schema_version":"1.0","source":{"id":"2006.10803","kind":"arxiv","version":2}},"canonical_sha256":"9c12e61de9ace2b47f4200ea83d7594e45cb380daec90e712686b3df4556d475","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c12e61de9ace2b47f4200ea83d7594e45cb380daec90e712686b3df4556d475","first_computed_at":"2026-07-05T01:56:19.677455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:19.677455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lD9y8gl84OyK2oDEhuLxxa1Y6l6PuD9utLCL+Y9kStjVqr78wApb+VlaGdaMbZA8Fxk5f0AFhCY2fMR2b1X9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:19.677894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee9c9e2db061d088918d9b2d84be8984667195b11b8020f26533bb1bdadd0767","sha256:4c8788a5a00abfce486706d39eb24ed550a28644f19bd6768c10b6cc1b19ed88"],"state_sha256":"603671f1774688ed87c344f9f8d0416a5a1031272112886fc3b3559757923156"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"utyXcQHzkN+nn0nbNl8kCFb9w1BWptoLx1iNPvQxlvCT57EYkwLUMDFBiSiMo/6tudfpMzBqlnWTDr11cIdIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:20:02.491552Z","bundle_sha256":"56e88941482e322673ddb9f70eba7c808d0df789affbb41501eca6af564ce365"}}