{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PLDXV4XRDU2UMWB3CRPEF7VGJY","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":"8df619f6013aed777ea4c33ef9250aa05535ce341d8228b968c878642f0e4c3f","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T10:49:09Z","title_canon_sha256":"864fbd713629b5853ef21307913c505cab10b494ad95a0b49c3492705875c8b3"},"schema_version":"1.0","source":{"id":"2112.04222","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04222","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04222v3","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04222","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PLDXV4XRDU2U","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"PLDXV4XRDU2UMWB3","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"PLDXV4XR","created_at":"2026-07-05T04:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:de0793d5390609487125dab15eb61ba73a87da2de768d6dbadc182d79029d20c","target":"graph","created_at":"2026-07-05T04:04:44Z","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/2112.04222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Today's VidSGG models are all proposal-based methods, i.e., they first generate numerous paired subject-object snippets as proposals, and then conduct predicate classification for each proposal. In this paper, we argue that this prevalent proposal-based framework has three inherent drawbacks: 1) The ground-truth predicate labels for proposals are partially correct. 2) They break the high-order relations among different predicate instances of a same subject-object pair. 3) VidSGG performance is upper-bounded by the quality of the proposals. To this end, we propose a new classification-then-grou","authors_text":"Jian Shao, Jun Xiao, Kaifeng Gao, Long Chen, Yulei Niu","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T10:49:09Z","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04222","kind":"arxiv","version":3},"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":"sha256:5f5dfa049037d95350cc2849e62f81a1118d09788c6fe1ff26c55b09a6452005","target":"record","created_at":"2026-07-05T04:04:44Z","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":"8df619f6013aed777ea4c33ef9250aa05535ce341d8228b968c878642f0e4c3f","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T10:49:09Z","title_canon_sha256":"864fbd713629b5853ef21307913c505cab10b494ad95a0b49c3492705875c8b3"},"schema_version":"1.0","source":{"id":"2112.04222","kind":"arxiv","version":3}},"canonical_sha256":"7ac77af2f11d3546583b145e42fea64e10573b45c0d9320321af7aeb8055b3f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ac77af2f11d3546583b145e42fea64e10573b45c0d9320321af7aeb8055b3f5","first_computed_at":"2026-07-05T04:04:44.216250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:44.216250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KvOhvUA8egycILgpftkzGfkIFtxZZwub+PXcVAkzncUMhN7g6+29uwVPNaRXwRWBOgla5Vsqm+iael8wPLyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:44.216687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04222","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f5dfa049037d95350cc2849e62f81a1118d09788c6fe1ff26c55b09a6452005","sha256:de0793d5390609487125dab15eb61ba73a87da2de768d6dbadc182d79029d20c"],"state_sha256":"8ae3f48f39b2379e6b64968710585eb024283e49367b57eeeffa28f38c4b0b73"}