{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SVDFBL5YBTIR3VZHKDIHIVD4F6","short_pith_number":"pith:SVDFBL5Y","canonical_record":{"source":{"id":"2010.04592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T14:18:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5c31ccf8ad2ab7e3acb0e91016ec3402636cf073482adda60134b480d1db2a38","abstract_canon_sha256":"9b8c4971abc04db3212764a538dae458e82f1e69a9a3fe1ebce7ed8248edd467"},"schema_version":"1.0"},"canonical_sha256":"954650afb80cd11dd72750d074547c2fbd38ba2b37d176345697bb03a50a114a","source":{"kind":"arxiv","id":"2010.04592","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04592","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04592v2","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04592","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"SVDFBL5YBTIR","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"SVDFBL5YBTIR3VZH","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"SVDFBL5Y","created_at":"2026-07-05T02:09:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SVDFBL5YBTIR3VZHKDIHIVD4F6","target":"record","payload":{"canonical_record":{"source":{"id":"2010.04592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T14:18:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5c31ccf8ad2ab7e3acb0e91016ec3402636cf073482adda60134b480d1db2a38","abstract_canon_sha256":"9b8c4971abc04db3212764a538dae458e82f1e69a9a3fe1ebce7ed8248edd467"},"schema_version":"1.0"},"canonical_sha256":"954650afb80cd11dd72750d074547c2fbd38ba2b37d176345697bb03a50a114a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:13.334293Z","signature_b64":"Oiccd1iq5mGaEp0uNtiBTSlu+5kERr6qCPaRXX7+kjN2VQbIeeGBsbsdPUCdOiORnySqn6pvoDpssU1kFj+pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"954650afb80cd11dd72750d074547c2fbd38ba2b37d176345697bb03a50a114a","last_reissued_at":"2026-07-05T02:09:13.333824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:13.333824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.04592","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":"2026-07-05T02:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaFmukz8PlmOeZXoowGBu6GghW6aCUfN609TG7P2W8m0EIVxwCRh/pJA8l9t9YLXlkE1rBP6ELNawveBYuq/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:29.929480Z"},"content_sha256":"d53a215e31e0cc0453430151380e51364b4d7f872aa54d342439d3fd7c42498b","schema_version":"1.0","event_id":"sha256:d53a215e31e0cc0453430151380e51364b4d7f872aa54d342439d3fd7c42498b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SVDFBL5YBTIR3VZHKDIHIVD4F6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Learning with Hard Negative Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ching-Yao Chuang, Joshua Robinson, Stefanie Jegelka, Suvrit Sra","submitted_at":"2020-10-09T14:18:53Z","abstract_excerpt":"How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an anchor point). The key challenge toward using hard negatives is that contrastive methods must remain unsupervised, making it infeasible to adopt existing negative sampling strategies that use true similarity information. In response, we develop a new family of unsupervised sampling methods for selecting hard negative samples where the user can control the ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04592","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/2010.04592/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":"2026-07-05T02:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MotDhBfyIrDc1cNwYEMg2Tuz/rf+ik7XxDt2N/pjs1NxpyAMliiHeoKslxi6j3JQGfmJb4Qy7raJLmIpBi9yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:29.930009Z"},"content_sha256":"c6c3390f1a77105020b603f20b132c5d60b16951a5035d24e0575139e3ec3751","schema_version":"1.0","event_id":"sha256:c6c3390f1a77105020b603f20b132c5d60b16951a5035d24e0575139e3ec3751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/bundle.json","state_url":"https://pith.science/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/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":"2026-08-07T07:16:29Z","links":{"resolver":"https://pith.science/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6","bundle":"https://pith.science/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/bundle.json","state":"https://pith.science/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVDFBL5YBTIR3VZHKDIHIVD4F6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SVDFBL5YBTIR3VZHKDIHIVD4F6","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":"9b8c4971abc04db3212764a538dae458e82f1e69a9a3fe1ebce7ed8248edd467","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T14:18:53Z","title_canon_sha256":"5c31ccf8ad2ab7e3acb0e91016ec3402636cf073482adda60134b480d1db2a38"},"schema_version":"1.0","source":{"id":"2010.04592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04592","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04592v2","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04592","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"SVDFBL5YBTIR","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"SVDFBL5YBTIR3VZH","created_at":"2026-07-05T02:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"SVDFBL5Y","created_at":"2026-07-05T02:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:c6c3390f1a77105020b603f20b132c5d60b16951a5035d24e0575139e3ec3751","target":"graph","created_at":"2026-07-05T02:09:13Z","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/2010.04592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an anchor point). The key challenge toward using hard negatives is that contrastive methods must remain unsupervised, making it infeasible to adopt existing negative sampling strategies that use true similarity information. In response, we develop a new family of unsupervised sampling methods for selecting hard negative samples where the user can control the ha","authors_text":"Ching-Yao Chuang, Joshua Robinson, Stefanie Jegelka, Suvrit Sra","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T14:18:53Z","title":"Contrastive Learning with Hard Negative Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04592","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:d53a215e31e0cc0453430151380e51364b4d7f872aa54d342439d3fd7c42498b","target":"record","created_at":"2026-07-05T02:09:13Z","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":"9b8c4971abc04db3212764a538dae458e82f1e69a9a3fe1ebce7ed8248edd467","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-09T14:18:53Z","title_canon_sha256":"5c31ccf8ad2ab7e3acb0e91016ec3402636cf073482adda60134b480d1db2a38"},"schema_version":"1.0","source":{"id":"2010.04592","kind":"arxiv","version":2}},"canonical_sha256":"954650afb80cd11dd72750d074547c2fbd38ba2b37d176345697bb03a50a114a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"954650afb80cd11dd72750d074547c2fbd38ba2b37d176345697bb03a50a114a","first_computed_at":"2026-07-05T02:09:13.333824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:09:13.333824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oiccd1iq5mGaEp0uNtiBTSlu+5kERr6qCPaRXX7+kjN2VQbIeeGBsbsdPUCdOiORnySqn6pvoDpssU1kFj+pAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:09:13.334293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d53a215e31e0cc0453430151380e51364b4d7f872aa54d342439d3fd7c42498b","sha256:c6c3390f1a77105020b603f20b132c5d60b16951a5035d24e0575139e3ec3751"],"state_sha256":"070654b4504eccd462c4e6451fb74dd101b714e44d337876ee6a6c0ccb439c35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PueDNS0ar9L9Zdo9TcZX88sgCKVGAdOAO+ejaeVYfQ+1aKCmLkDPvBi7oPr6TLP+obfqXsFbwEaB2bV8nf5eBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:16:29.933916Z","bundle_sha256":"645f298e0524dd6eb21a30593d2d1289fbdd02811bfb6a831fb0db1836bd2d0d"}}