{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LV2UE2G45MCQ75OLPGWCOGBVGP","short_pith_number":"pith:LV2UE2G4","canonical_record":{"source":{"id":"2011.01403","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T01:10:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbc44b5886b2d02caba2a195c14dfe2d6399326fbc6864a32a5021fee7126f77","abstract_canon_sha256":"d1f18127d63ffa9aa7fa32986b31485f0ee400e3fed0f73aee8f19a691c003cc"},"schema_version":"1.0"},"canonical_sha256":"5d754268dceb050ff5cb79ac27183533cb8e4bd42fddb654aa50c4fdef25bd8d","source":{"kind":"arxiv","id":"2011.01403","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01403","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01403v3","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01403","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_12","alias_value":"LV2UE2G45MCQ","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_16","alias_value":"LV2UE2G45MCQ75OL","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_8","alias_value":"LV2UE2G4","created_at":"2026-07-05T02:28:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LV2UE2G45MCQ75OLPGWCOGBVGP","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01403","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T01:10:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbc44b5886b2d02caba2a195c14dfe2d6399326fbc6864a32a5021fee7126f77","abstract_canon_sha256":"d1f18127d63ffa9aa7fa32986b31485f0ee400e3fed0f73aee8f19a691c003cc"},"schema_version":"1.0"},"canonical_sha256":"5d754268dceb050ff5cb79ac27183533cb8e4bd42fddb654aa50c4fdef25bd8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:53.097270Z","signature_b64":"Jj3JZqtxoH6JrgA3mPPUPl8gLWSnTeUOafKZYNcIS5lqkMbzPWWjPriA9wwv7iMViqpn83Y44+gWXJXhbouTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d754268dceb050ff5cb79ac27183533cb8e4bd42fddb654aa50c4fdef25bd8d","last_reissued_at":"2026-07-05T02:28:53.096812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:53.096812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01403","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:28:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8hMzeId1Y1o60JyLmQFNRnJ8HnVhXFKNCxXG793JpR6voVVleKtV1rorSSkvSt3+jWmiYSN0B0YzOXdt3rtWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:45:35.885708Z"},"content_sha256":"bb044429874d9739a5c090628a6cf94e3950f2d8738af3ba7eb98bdfaa7d4710","schema_version":"1.0","event_id":"sha256:bb044429874d9739a5c090628a6cf94e3950f2d8738af3ba7eb98bdfaa7d4710"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LV2UE2G45MCQ75OLPGWCOGBVGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Beliz Gunel, Jingfei Du, Ves Stoyanov","submitted_at":"2020-11-03T01:10:39Z","abstract_excerpt":"State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss. However, the cross-entropy loss has several shortcomings that can lead to sub-optimal generalization and instability. Driven by the intuition that good generalization requires capturing the similarity between examples in one class and contrasting them with examples in other classes, we propose a supervised contrastive learning (SCL) objective for the fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01403","kind":"arxiv","version":3},"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/2011.01403/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":"2026-07-05T02:28:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LbJrc6hwMnWmxTt1v0AI33QcGPQYiLH5NCXkyzKng0ubCC7kE9y5loY7y4ozJR5bxd3FB4CcnuIFnw8g9I5HDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:45:35.886218Z"},"content_sha256":"eb401f81beb903c65c97a9b55d740bf553f2ead52f141ed14cf2082e372cd065","schema_version":"1.0","event_id":"sha256:eb401f81beb903c65c97a9b55d740bf553f2ead52f141ed14cf2082e372cd065"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/bundle.json","state_url":"https://pith.science/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/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":"2026-08-19T07:45:35Z","links":{"resolver":"https://pith.science/pith/LV2UE2G45MCQ75OLPGWCOGBVGP","bundle":"https://pith.science/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/bundle.json","state":"https://pith.science/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LV2UE2G45MCQ75OLPGWCOGBVGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LV2UE2G45MCQ75OLPGWCOGBVGP","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":"d1f18127d63ffa9aa7fa32986b31485f0ee400e3fed0f73aee8f19a691c003cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T01:10:39Z","title_canon_sha256":"fbc44b5886b2d02caba2a195c14dfe2d6399326fbc6864a32a5021fee7126f77"},"schema_version":"1.0","source":{"id":"2011.01403","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01403","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01403v3","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01403","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_12","alias_value":"LV2UE2G45MCQ","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_16","alias_value":"LV2UE2G45MCQ75OL","created_at":"2026-07-05T02:28:53Z"},{"alias_kind":"pith_short_8","alias_value":"LV2UE2G4","created_at":"2026-07-05T02:28:53Z"}],"graph_snapshots":[{"event_id":"sha256:eb401f81beb903c65c97a9b55d740bf553f2ead52f141ed14cf2082e372cd065","target":"graph","created_at":"2026-07-05T02:28:53Z","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/2011.01403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss. However, the cross-entropy loss has several shortcomings that can lead to sub-optimal generalization and instability. Driven by the intuition that good generalization requires capturing the similarity between examples in one class and contrasting them with examples in other classes, we propose a supervised contrastive learning (SCL) objective for the fine-tun","authors_text":"Alexis Conneau, Beliz Gunel, Jingfei Du, Ves Stoyanov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T01:10:39Z","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01403","kind":"arxiv","version":3},"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:bb044429874d9739a5c090628a6cf94e3950f2d8738af3ba7eb98bdfaa7d4710","target":"record","created_at":"2026-07-05T02:28:53Z","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":"d1f18127d63ffa9aa7fa32986b31485f0ee400e3fed0f73aee8f19a691c003cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T01:10:39Z","title_canon_sha256":"fbc44b5886b2d02caba2a195c14dfe2d6399326fbc6864a32a5021fee7126f77"},"schema_version":"1.0","source":{"id":"2011.01403","kind":"arxiv","version":3}},"canonical_sha256":"5d754268dceb050ff5cb79ac27183533cb8e4bd42fddb654aa50c4fdef25bd8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d754268dceb050ff5cb79ac27183533cb8e4bd42fddb654aa50c4fdef25bd8d","first_computed_at":"2026-07-05T02:28:53.096812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:53.096812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jj3JZqtxoH6JrgA3mPPUPl8gLWSnTeUOafKZYNcIS5lqkMbzPWWjPriA9wwv7iMViqpn83Y44+gWXJXhbouTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:53.097270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01403","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb044429874d9739a5c090628a6cf94e3950f2d8738af3ba7eb98bdfaa7d4710","sha256:eb401f81beb903c65c97a9b55d740bf553f2ead52f141ed14cf2082e372cd065"],"state_sha256":"a74565e204198132f53a557753b485d96f575c8849808dd4f144ca46e91373d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vXM8Pxbc+FQj5dgKgGalOrGMWqON++lJ7nINSzmCEq4ID9nPE64smKsURfTZ9/qOAkCXy8FdZ2pvNa/6mxD6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:45:35.890505Z","bundle_sha256":"6e8015cec37485df5da5e3cef3d4c82c5906730416b17741b6c603fc950ce344"}}