{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DYXEL6BNHIRDTK5PEF5RNAK42K","short_pith_number":"pith:DYXEL6BN","schema_version":"1.0","canonical_sha256":"1e2e45f82d3a2239abaf217b16815cd2a0728e55713f7216fc7911a7ea72ef16","source":{"kind":"arxiv","id":"2203.13049","version":2},"attestation_state":"computed","paper":{"title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Juncheng Li, Junlin Xie, Linchao Zhu, Long Qian, Siliang Tang, Xin Eric Wang, Yi Yang, Yueting Zhuang","submitted_at":"2022-03-24T12:55:23Z","abstract_excerpt":"Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. Thanks to the semantic diversity of natural language descriptions, temporal grounding allows activity grounding beyond pre-defined classes and has received increasing attention in recent years. The semantic diversity is rooted in the principle of compositionality in linguistics, where novel semantics can be systematically described by combining known words in novel ways (compositional generalization). However, current temporal grounding datasets do not specifically te"},"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":"2203.13049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T12:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"8516920a6118f21622b7100538c14b5ae27d04a70090d66c0f69e69080f1234f","abstract_canon_sha256":"cefc84c171e181de4748f38c9e13992c31d26498b477a5314261489e7892c8e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:03.425307Z","signature_b64":"Qcqw+6CDU3B8T5BZgLKdDqrxRJBkqh+ZpQ4SMpqB73cnCDsVgxTtV0+7fJ4BTv17k0urBMMqibOmsacMGrSKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2e45f82d3a2239abaf217b16815cd2a0728e55713f7216fc7911a7ea72ef16","last_reissued_at":"2026-07-05T04:09:03.424922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:03.424922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wu, Juncheng Li, Junlin Xie, Linchao Zhu, Long Qian, Siliang Tang, Xin Eric Wang, Yi Yang, Yueting Zhuang","submitted_at":"2022-03-24T12:55:23Z","abstract_excerpt":"Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. Thanks to the semantic diversity of natural language descriptions, temporal grounding allows activity grounding beyond pre-defined classes and has received increasing attention in recent years. The semantic diversity is rooted in the principle of compositionality in linguistics, where novel semantics can be systematically described by combining known words in novel ways (compositional generalization). However, current temporal grounding datasets do not specifically te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13049","kind":"arxiv","version":2},"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/2203.13049/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":"2203.13049","created_at":"2026-07-05T04:09:03.424978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13049v2","created_at":"2026-07-05T04:09:03.424978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13049","created_at":"2026-07-05T04:09:03.424978+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYXEL6BNHIRD","created_at":"2026-07-05T04:09:03.424978+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYXEL6BNHIRDTK5P","created_at":"2026-07-05T04:09:03.424978+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYXEL6BN","created_at":"2026-07-05T04:09:03.424978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07972","citing_title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K","json":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K.json","graph_json":"https://pith.science/api/pith-number/DYXEL6BNHIRDTK5PEF5RNAK42K/graph.json","events_json":"https://pith.science/api/pith-number/DYXEL6BNHIRDTK5PEF5RNAK42K/events.json","paper":"https://pith.science/paper/DYXEL6BN"},"agent_actions":{"view_html":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K","download_json":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K.json","view_paper":"https://pith.science/paper/DYXEL6BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13049&json=true","fetch_graph":"https://pith.science/api/pith-number/DYXEL6BNHIRDTK5PEF5RNAK42K/graph.json","fetch_events":"https://pith.science/api/pith-number/DYXEL6BNHIRDTK5PEF5RNAK42K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K/action/storage_attestation","attest_author":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K/action/author_attestation","sign_citation":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K/action/citation_signature","submit_replication":"https://pith.science/pith/DYXEL6BNHIRDTK5PEF5RNAK42K/action/replication_record"}},"created_at":"2026-07-05T04:09:03.424978+00:00","updated_at":"2026-07-05T04:09:03.424978+00:00"}