{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5FZUALBHYSO4LMVLGK4FGFDFAZ","short_pith_number":"pith:5FZUALBH","schema_version":"1.0","canonical_sha256":"e973402c27c49dc5b2ab32b8531465067419c960ebfabb054c44dd613ffceec0","source":{"kind":"arxiv","id":"2010.06682","version":2},"attestation_state":"computed","paper":{"title":"Are all negatives created equal in contrastive instance discrimination?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ari S. Morcos, David J. Schwab, Jonathan Frankle, Tiffany Tianhui Cai","submitted_at":"2020-10-13T20:52:10Z","abstract_excerpt":"Self-supervised learning has recently begun to rival supervised learning on computer vision tasks. Many of the recent approaches have been based on contrastive instance discrimination (CID), in which the network is trained to recognize two augmented versions of the same instance (a query and positive) while discriminating against a pool of other instances (negatives). The learned representation is then used on downstream tasks such as image classification. Using methodology from MoCo v2 (Chen et al., 2020), we divided negatives by their difficulty for a given query and studied which difficulty"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.06682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-13T20:52:10Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"c95c92839933652db424e50289a8247be2b143f90e3b987db0bd9744212f179b","abstract_canon_sha256":"c36d0f0c61a283dd10351a6758ba0813de1dd55ae7bd38f6f45ee4716c2cc83a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:45.559487Z","signature_b64":"91BwuPKfKvQd2u+QNvkhFrjKXR/Pfq6LHbmUvYo0HmiNwpo+3fLnygG/JY6hH7DWM7LUvYs0knj9Vo9MnBlWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e973402c27c49dc5b2ab32b8531465067419c960ebfabb054c44dd613ffceec0","last_reissued_at":"2026-07-05T01:45:45.559072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:45.559072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are all negatives created equal in contrastive instance discrimination?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ari S. Morcos, David J. Schwab, Jonathan Frankle, Tiffany Tianhui Cai","submitted_at":"2020-10-13T20:52:10Z","abstract_excerpt":"Self-supervised learning has recently begun to rival supervised learning on computer vision tasks. Many of the recent approaches have been based on contrastive instance discrimination (CID), in which the network is trained to recognize two augmented versions of the same instance (a query and positive) while discriminating against a pool of other instances (negatives). The learned representation is then used on downstream tasks such as image classification. Using methodology from MoCo v2 (Chen et al., 2020), we divided negatives by their difficulty for a given query and studied which difficulty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06682","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/2010.06682/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.06682","created_at":"2026-07-05T01:45:45.559127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06682v2","created_at":"2026-07-05T01:45:45.559127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06682","created_at":"2026-07-05T01:45:45.559127+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FZUALBHYSO4","created_at":"2026-07-05T01:45:45.559127+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FZUALBHYSO4LMVL","created_at":"2026-07-05T01:45:45.559127+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FZUALBH","created_at":"2026-07-05T01:45:45.559127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.09523","citing_title":"Patch-Wise Hypergraph Contrastive Learning with Dual Normal Distribution Weighting for Multi-Domain Stain Transfer","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18460","citing_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13313","citing_title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ","json":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ.json","graph_json":"https://pith.science/api/pith-number/5FZUALBHYSO4LMVLGK4FGFDFAZ/graph.json","events_json":"https://pith.science/api/pith-number/5FZUALBHYSO4LMVLGK4FGFDFAZ/events.json","paper":"https://pith.science/paper/5FZUALBH"},"agent_actions":{"view_html":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ","download_json":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ.json","view_paper":"https://pith.science/paper/5FZUALBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06682&json=true","fetch_graph":"https://pith.science/api/pith-number/5FZUALBHYSO4LMVLGK4FGFDFAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5FZUALBHYSO4LMVLGK4FGFDFAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ/action/storage_attestation","attest_author":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ/action/author_attestation","sign_citation":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ/action/citation_signature","submit_replication":"https://pith.science/pith/5FZUALBHYSO4LMVLGK4FGFDFAZ/action/replication_record"}},"created_at":"2026-07-05T01:45:45.559127+00:00","updated_at":"2026-07-05T01:45:45.559127+00:00"}