{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HNQSTB6RMN3KYLDOZYQHORPDST","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":"56da6373084324f3a81a2ed4b74c93cd0e97b4fc3ad450cc8b804e0a36895127","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T15:48:47Z","title_canon_sha256":"6f45e51bcf20f2c0ec02261fa1d0345953b1040fc698c28ec84451b612f60623"},"schema_version":"1.0","source":{"id":"2305.12218","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12218","created_at":"2026-07-05T06:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12218v1","created_at":"2026-07-05T06:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12218","created_at":"2026-07-05T06:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"HNQSTB6RMN3K","created_at":"2026-07-05T06:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"HNQSTB6RMN3KYLDO","created_at":"2026-07-05T06:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"HNQSTB6R","created_at":"2026-07-05T06:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:e25242331737059edd72c577bcf8fb13f6bb0e9562a7866c60808ed3f2348a04","target":"graph","created_at":"2026-07-05T06:12:07Z","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/2305.12218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set ali","authors_text":"Chang Liu, Hao Li, Jie Chen, Jinfa Huang, Li Yuan, Peng Jin, Zesen Cheng, Zhennan Wang","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T15:48:47Z","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12218","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":"sha256:44ac802d2f0ae0e62b010cfacb688585796a0dc011ae0c94ef0f5530778bff44","target":"record","created_at":"2026-07-05T06:12:07Z","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":"56da6373084324f3a81a2ed4b74c93cd0e97b4fc3ad450cc8b804e0a36895127","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T15:48:47Z","title_canon_sha256":"6f45e51bcf20f2c0ec02261fa1d0345953b1040fc698c28ec84451b612f60623"},"schema_version":"1.0","source":{"id":"2305.12218","kind":"arxiv","version":1}},"canonical_sha256":"3b612987d16376ac2c6ece207745e394c2c4125c55a09c1b7989562f66f551c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b612987d16376ac2c6ece207745e394c2c4125c55a09c1b7989562f66f551c2","first_computed_at":"2026-07-05T06:12:07.997408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:07.997408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tb90pRzxMh1LkZfA6G/LFNk3fOBLqJ/LCZXQIWMLD+bo/FhAyBPw3WdN/wTOUxH4n6e7moPeg3TAILLj2TNaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:07.997842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12218","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44ac802d2f0ae0e62b010cfacb688585796a0dc011ae0c94ef0f5530778bff44","sha256:e25242331737059edd72c577bcf8fb13f6bb0e9562a7866c60808ed3f2348a04"],"state_sha256":"c5d97b00a791157d7974f146f87756f0aa82d1b6992140df42462b4f6bd1bc1e"}