{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CUIPL563MRSABCOD675DENGSZO","short_pith_number":"pith:CUIPL563","schema_version":"1.0","canonical_sha256":"1510f5f7db64640089c3f7fa3234d2cbb184a75041747b79abbda15e2b261b6f","source":{"kind":"arxiv","id":"2309.13237","version":3},"attestation_state":"computed","paper":{"title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hefeng Wu, Liang Lin, Tao Pu, Tianshui Chen, Yongyi Lu","submitted_at":"2023-09-23T02:40:28Z","abstract_excerpt":"Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-tempor"},"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":"2309.13237","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-23T02:40:28Z","cross_cats_sorted":[],"title_canon_sha256":"31e4542c3bc77ee954040131633021fb0b26bd75bff1c023b62a96d0747c1071","abstract_canon_sha256":"5d11cf9318e0e9b01d42550ffd08873c00e62ae00e071bf991f65b6cf0dd2c0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:20.755665Z","signature_b64":"ZLWymBLXSCPaJMiV1v/j14upaGq9o6QKdLFSP8j8BGJYV857wrw934hcIjcXfUpQtMLv7YAOPDs6oPh0SzFIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1510f5f7db64640089c3f7fa3234d2cbb184a75041747b79abbda15e2b261b6f","last_reissued_at":"2026-07-05T07:24:20.755223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:20.755223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hefeng Wu, Liang Lin, Tao Pu, Tianshui Chen, Yongyi Lu","submitted_at":"2023-09-23T02:40:28Z","abstract_excerpt":"Video scene graph generation (VidSGG) aims to identify objects in visual scenes and infer their relationships for a given video. It requires not only a comprehensive understanding of each object scattered on the whole scene but also a deep dive into their temporal motions and interactions. Inherently, object pairs and their relationships enjoy spatial co-occurrence correlations within each image and temporal consistency/transition correlations across different images, which can serve as prior knowledge to facilitate VidSGG model learning and inference. In this work, we propose a spatial-tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13237","kind":"arxiv","version":3},"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/2309.13237/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":"2309.13237","created_at":"2026-07-05T07:24:20.755277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13237v3","created_at":"2026-07-05T07:24:20.755277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13237","created_at":"2026-07-05T07:24:20.755277+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUIPL563MRSA","created_at":"2026-07-05T07:24:20.755277+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUIPL563MRSABCOD","created_at":"2026-07-05T07:24:20.755277+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUIPL563","created_at":"2026-07-05T07:24:20.755277+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/CUIPL563MRSABCOD675DENGSZO","json":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO.json","graph_json":"https://pith.science/api/pith-number/CUIPL563MRSABCOD675DENGSZO/graph.json","events_json":"https://pith.science/api/pith-number/CUIPL563MRSABCOD675DENGSZO/events.json","paper":"https://pith.science/paper/CUIPL563"},"agent_actions":{"view_html":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO","download_json":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO.json","view_paper":"https://pith.science/paper/CUIPL563","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13237&json=true","fetch_graph":"https://pith.science/api/pith-number/CUIPL563MRSABCOD675DENGSZO/graph.json","fetch_events":"https://pith.science/api/pith-number/CUIPL563MRSABCOD675DENGSZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO/action/storage_attestation","attest_author":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO/action/author_attestation","sign_citation":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO/action/citation_signature","submit_replication":"https://pith.science/pith/CUIPL563MRSABCOD675DENGSZO/action/replication_record"}},"created_at":"2026-07-05T07:24:20.755277+00:00","updated_at":"2026-07-05T07:24:20.755277+00:00"}