{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2AB5RH6JXKO4YPYN3I22RGPMLF","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":"ba35ec6775113f5c3da2a479bce5511c54ea18e53e8cef475cc5f2506f46bf62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T09:08:21Z","title_canon_sha256":"1d6438f07d138429a44a979c102a1d050b3019e36274bd3af4d7d251df3c2e98"},"schema_version":"1.0","source":{"id":"2608.00551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00551","created_at":"2026-08-04T00:37:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00551v1","created_at":"2026-08-04T00:37:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00551","created_at":"2026-08-04T00:37:25Z"},{"alias_kind":"pith_short_12","alias_value":"2AB5RH6JXKO4","created_at":"2026-08-04T00:37:25Z"},{"alias_kind":"pith_short_16","alias_value":"2AB5RH6JXKO4YPYN","created_at":"2026-08-04T00:37:25Z"},{"alias_kind":"pith_short_8","alias_value":"2AB5RH6J","created_at":"2026-08-04T00:37:25Z"}],"graph_snapshots":[{"event_id":"sha256:d20701620ca7c8623641a9376042d9b90dc3a4f2533406512e3eac444be10c86","target":"graph","created_at":"2026-08-04T00:37:25Z","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/2608.00551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Genke Yang, Jian Chu, Kezhao Yin, Xiaolun Jing, Xinxing Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T09:08:21Z","title":"PHA-Net: Prototype-based Hierarchical Alignment Network for Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00551","kind":"arxiv","version":1},"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:a7170a3c006e2115f29eeb56f6abdd89dc84add0a7010d62797ca819daf0be7b","target":"record","created_at":"2026-08-04T00:37:25Z","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":"ba35ec6775113f5c3da2a479bce5511c54ea18e53e8cef475cc5f2506f46bf62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-01T09:08:21Z","title_canon_sha256":"1d6438f07d138429a44a979c102a1d050b3019e36274bd3af4d7d251df3c2e98"},"schema_version":"1.0","source":{"id":"2608.00551","kind":"arxiv","version":1}},"canonical_sha256":"d003d89fc9ba9dcc3f0dda35a899ec594107795d6a4195203c27b281c79efb8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d003d89fc9ba9dcc3f0dda35a899ec594107795d6a4195203c27b281c79efb8d","first_computed_at":"2026-08-04T00:37:25.580443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:37:25.580443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9mzUUAr9YLvFn2tTIlIyDtGbA4aaEqpr4kn7FiG/ws1p/xju8jKcs5Czc3pLIc7sRrOBOaaOlTeNp7jnSwAuCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T00:37:25.581803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7170a3c006e2115f29eeb56f6abdd89dc84add0a7010d62797ca819daf0be7b","sha256:d20701620ca7c8623641a9376042d9b90dc3a4f2533406512e3eac444be10c86"],"state_sha256":"f93b31ef93a3c03a943e9a2b06fa7ba22f3e09820ba723e85638e61c8d0b85e4"}