{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2AB5RH6JXKO4YPYN3I22RGPMLF","short_pith_number":"pith:2AB5RH6J","schema_version":"1.0","canonical_sha256":"d003d89fc9ba9dcc3f0dda35a899ec594107795d6a4195203c27b281c79efb8d","source":{"kind":"arxiv","id":"2608.00551","version":1},"attestation_state":"computed","paper":{"title":"PHA-Net: Prototype-based Hierarchical Alignment Network for Text-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Genke Yang, Jian Chu, Kezhao Yin, Xiaolun Jing, Xinxing Yang","submitted_at":"2026-08-01T09:08:21Z","abstract_excerpt":"With the emergence of large-scale image-text pre-training models, e.g., CLIP, text-video retrieval has experienced substantial advances in recent years. Existing best-performing methods involve aligning cross-modal semantics at individual, local, and global levels simultaneously, raising concerns about the intrinsic semantic mismatch between concise texts and rich videos. A canonical approach is to integrate multiple language-video attention modules into the hierarchical framework while this paradigm only optimizes visual representations with prohibitive computational costs. In this paper, we "},"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":"2608.00551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T09:08:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d6438f07d138429a44a979c102a1d050b3019e36274bd3af4d7d251df3c2e98","abstract_canon_sha256":"ba35ec6775113f5c3da2a479bce5511c54ea18e53e8cef475cc5f2506f46bf62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:25.581803Z","signature_b64":"9mzUUAr9YLvFn2tTIlIyDtGbA4aaEqpr4kn7FiG/ws1p/xju8jKcs5Czc3pLIc7sRrOBOaaOlTeNp7jnSwAuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d003d89fc9ba9dcc3f0dda35a899ec594107795d6a4195203c27b281c79efb8d","last_reissued_at":"2026-08-04T00:37:25.580443Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:25.580443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PHA-Net: Prototype-based Hierarchical Alignment Network for Text-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Genke Yang, Jian Chu, Kezhao Yin, Xiaolun Jing, Xinxing Yang","submitted_at":"2026-08-01T09:08:21Z","abstract_excerpt":"With the emergence of large-scale image-text pre-training models, e.g., CLIP, text-video retrieval has experienced substantial advances in recent years. Existing best-performing methods involve aligning cross-modal semantics at individual, local, and global levels simultaneously, raising concerns about the intrinsic semantic mismatch between concise texts and rich videos. A canonical approach is to integrate multiple language-video attention modules into the hierarchical framework while this paradigm only optimizes visual representations with prohibitive computational costs. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00551","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/2608.00551/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":"2608.00551","created_at":"2026-08-04T00:37:25.581618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00551v1","created_at":"2026-08-04T00:37:25.581618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00551","created_at":"2026-08-04T00:37:25.581618+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AB5RH6JXKO4","created_at":"2026-08-04T00:37:25.581618+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AB5RH6JXKO4YPYN","created_at":"2026-08-04T00:37:25.581618+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AB5RH6J","created_at":"2026-08-04T00:37:25.581618+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/2AB5RH6JXKO4YPYN3I22RGPMLF","json":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF.json","graph_json":"https://pith.science/api/pith-number/2AB5RH6JXKO4YPYN3I22RGPMLF/graph.json","events_json":"https://pith.science/api/pith-number/2AB5RH6JXKO4YPYN3I22RGPMLF/events.json","paper":"https://pith.science/paper/2AB5RH6J"},"agent_actions":{"view_html":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF","download_json":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF.json","view_paper":"https://pith.science/paper/2AB5RH6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00551&json=true","fetch_graph":"https://pith.science/api/pith-number/2AB5RH6JXKO4YPYN3I22RGPMLF/graph.json","fetch_events":"https://pith.science/api/pith-number/2AB5RH6JXKO4YPYN3I22RGPMLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF/action/storage_attestation","attest_author":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF/action/author_attestation","sign_citation":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF/action/citation_signature","submit_replication":"https://pith.science/pith/2AB5RH6JXKO4YPYN3I22RGPMLF/action/replication_record"}},"created_at":"2026-08-04T00:37:25.581618+00:00","updated_at":"2026-08-04T00:37:25.581618+00:00"}