{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SUKLLQXEVSRTGW3ZWCELZP3DFS","short_pith_number":"pith:SUKLLQXE","schema_version":"1.0","canonical_sha256":"9514b5c2e4aca3335b79b088bcbf632ca87df4a1e26b12cb388e72028e9575a3","source":{"kind":"arxiv","id":"2501.16360","version":1},"attestation_state":"computed","paper":{"title":"Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Duy Hoang, Gia Bao, Huy Ngo, Huy Phan, Khoi Pham, Tri Nguyen","submitted_at":"2025-01-20T22:01:52Z","abstract_excerpt":"Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional approaches often overlook the full potential of key embeddings and are susceptible to performance degradation from noisy negative samples in the memory bank. This study addresses these challenges by proposing an enhanced contrastive learning framework that incorporates two key innovations. First, we introduce a dual-view loss function, which ensures balanced optimi"},"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":"2501.16360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-20T22:01:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c329f8e4b20cd948c27e5c5782a0c690df830e76154dc503c2bf160ac062b824","abstract_canon_sha256":"a28cbf163a232351b2433ac085bb6a4ad1be7a5fc6512dfada48af2f3f8ce9a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:11.808388Z","signature_b64":"8M8uLd2U4l9t/dGknKyv1CnFRcLfvhmFeTuZGK3Jdp8OnV9t2WcsUxy6BnacVgl5OPiUG09UfmFdPuBEnzpyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9514b5c2e4aca3335b79b088bcbf632ca87df4a1e26b12cb388e72028e9575a3","last_reissued_at":"2026-07-05T10:06:11.807956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:11.807956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Duy Hoang, Gia Bao, Huy Ngo, Huy Phan, Khoi Pham, Tri Nguyen","submitted_at":"2025-01-20T22:01:52Z","abstract_excerpt":"Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional approaches often overlook the full potential of key embeddings and are susceptible to performance degradation from noisy negative samples in the memory bank. This study addresses these challenges by proposing an enhanced contrastive learning framework that incorporates two key innovations. First, we introduce a dual-view loss function, which ensures balanced optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16360","kind":"arxiv","version":1},"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/2501.16360/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":"2501.16360","created_at":"2026-07-05T10:06:11.808021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16360v1","created_at":"2026-07-05T10:06:11.808021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16360","created_at":"2026-07-05T10:06:11.808021+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUKLLQXEVSRT","created_at":"2026-07-05T10:06:11.808021+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUKLLQXEVSRTGW3Z","created_at":"2026-07-05T10:06:11.808021+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUKLLQXE","created_at":"2026-07-05T10:06:11.808021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS","json":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS.json","graph_json":"https://pith.science/api/pith-number/SUKLLQXEVSRTGW3ZWCELZP3DFS/graph.json","events_json":"https://pith.science/api/pith-number/SUKLLQXEVSRTGW3ZWCELZP3DFS/events.json","paper":"https://pith.science/paper/SUKLLQXE"},"agent_actions":{"view_html":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS","download_json":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS.json","view_paper":"https://pith.science/paper/SUKLLQXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16360&json=true","fetch_graph":"https://pith.science/api/pith-number/SUKLLQXEVSRTGW3ZWCELZP3DFS/graph.json","fetch_events":"https://pith.science/api/pith-number/SUKLLQXEVSRTGW3ZWCELZP3DFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS/action/storage_attestation","attest_author":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS/action/author_attestation","sign_citation":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS/action/citation_signature","submit_replication":"https://pith.science/pith/SUKLLQXEVSRTGW3ZWCELZP3DFS/action/replication_record"}},"created_at":"2026-07-05T10:06:11.808021+00:00","updated_at":"2026-07-05T10:06:11.808021+00:00"}