{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZ2CADFWAN4FRQSS3TK4W5C6LW","short_pith_number":"pith:NZ2CADFW","schema_version":"1.0","canonical_sha256":"6e74200cb6037858c252dcd5cb745e5da2fcd6544e0d75ba82548e9aba8b4d07","source":{"kind":"arxiv","id":"2409.19865","version":1},"attestation_state":"computed","paper":{"title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingqing Zhang, Heming Du, Jiajun Liu, Sen Wang, Xin Yu, Xue Li, Zhuo Cao","submitted_at":"2024-09-30T01:49:37Z","abstract_excerpt":"Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(candidate) alignment paradigm, which struggles to discern nuanced differences among candidates, leading to frequent mismatches. Inspired by Comparative Judgement in human cognitive science, where decisions are made by directly comparing items rather than evaluating them independently, we propose TokenBinder. This innovative two-stage TVR framework int"},"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":"2409.19865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T01:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"cdb5defa4556552ff7a5f1403a774040216050d628bc6c7617612929d534cd0a","abstract_canon_sha256":"43b5bf6a5147b2dbb02de341a44a19a9a302cf8efa32c5ccb4421487918bfcf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:23.992938Z","signature_b64":"jUlp1SJdQi/2AWgXWw8J8H1ssIVSdM1VfP+L5k9VbJkXzmNdUEI012+7DmFnF2fPcIcmYRAJ1HdRJJtXoAuPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e74200cb6037858c252dcd5cb745e5da2fcd6544e0d75ba82548e9aba8b4d07","last_reissued_at":"2026-07-05T09:13:23.992462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:23.992462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingqing Zhang, Heming Du, Jiajun Liu, Sen Wang, Xin Yu, Xue Li, Zhuo Cao","submitted_at":"2024-09-30T01:49:37Z","abstract_excerpt":"Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(candidate) alignment paradigm, which struggles to discern nuanced differences among candidates, leading to frequent mismatches. Inspired by Comparative Judgement in human cognitive science, where decisions are made by directly comparing items rather than evaluating them independently, we propose TokenBinder. This innovative two-stage TVR framework int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19865","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/2409.19865/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":"2409.19865","created_at":"2026-07-05T09:13:23.992525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19865v1","created_at":"2026-07-05T09:13:23.992525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19865","created_at":"2026-07-05T09:13:23.992525+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ2CADFWAN4F","created_at":"2026-07-05T09:13:23.992525+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ2CADFWAN4FRQSS","created_at":"2026-07-05T09:13:23.992525+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ2CADFW","created_at":"2026-07-05T09:13:23.992525+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/NZ2CADFWAN4FRQSS3TK4W5C6LW","json":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW.json","graph_json":"https://pith.science/api/pith-number/NZ2CADFWAN4FRQSS3TK4W5C6LW/graph.json","events_json":"https://pith.science/api/pith-number/NZ2CADFWAN4FRQSS3TK4W5C6LW/events.json","paper":"https://pith.science/paper/NZ2CADFW"},"agent_actions":{"view_html":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW","download_json":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW.json","view_paper":"https://pith.science/paper/NZ2CADFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19865&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ2CADFWAN4FRQSS3TK4W5C6LW/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ2CADFWAN4FRQSS3TK4W5C6LW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW/action/storage_attestation","attest_author":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW/action/author_attestation","sign_citation":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW/action/citation_signature","submit_replication":"https://pith.science/pith/NZ2CADFWAN4FRQSS3TK4W5C6LW/action/replication_record"}},"created_at":"2026-07-05T09:13:23.992525+00:00","updated_at":"2026-07-05T09:13:23.992525+00:00"}