{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WTKQAT5TF3X3GEAS3NXYUIZQ5C","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":"0826f92b7d56c767983837383e2cc76e40685780213703f94b26f5b41a767274","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:24:39Z","title_canon_sha256":"0863ad8cec38af4a4895a62dbcdcf10bee47a415ab1f6f4eb363d2514fbe0e82"},"schema_version":"1.0","source":{"id":"2411.18042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18042","created_at":"2026-07-05T10:41:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18042v2","created_at":"2026-07-05T10:41:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18042","created_at":"2026-07-05T10:41:50Z"},{"alias_kind":"pith_short_12","alias_value":"WTKQAT5TF3X3","created_at":"2026-07-05T10:41:50Z"},{"alias_kind":"pith_short_16","alias_value":"WTKQAT5TF3X3GEAS","created_at":"2026-07-05T10:41:50Z"},{"alias_kind":"pith_short_8","alias_value":"WTKQAT5T","created_at":"2026-07-05T10:41:50Z"}],"graph_snapshots":[{"event_id":"sha256:1c134f2fbae6188e9505b6de5bfbb2852875ba1ba05517b36aa40e627eb8083e","target":"graph","created_at":"2026-07-05T10:41:50Z","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/2411.18042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal LLMs have advanced vision-language tasks but still struggle with understanding video scenes. To bridge this gap, Video Scene Graph Generation (VidSGG) has emerged to capture multi-object relationships across video frames. However, prior methods rely on pairwise connections, limiting their ability to handle complex multi-object interactions and reasoning. To this end, we propose Multimodal LLMs on a Scene HyperGraph (HyperGLM), promoting reasoning about multi-way interactions and higher-order relationships. Our approach uniquely integrates entity scene graphs, which capture spatial r","authors_text":"Alper Yilmaz, Jackson Cothren, Khoa Luu, Pha Nguyen, Trong-Thuan Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:24:39Z","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18042","kind":"arxiv","version":2},"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":"sha256:644c4364c9ecc6854be797d3509f9e1ebf3eef59cad5173f0c003cfd89ad3368","target":"record","created_at":"2026-07-05T10:41:50Z","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":"0826f92b7d56c767983837383e2cc76e40685780213703f94b26f5b41a767274","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T04:24:39Z","title_canon_sha256":"0863ad8cec38af4a4895a62dbcdcf10bee47a415ab1f6f4eb363d2514fbe0e82"},"schema_version":"1.0","source":{"id":"2411.18042","kind":"arxiv","version":2}},"canonical_sha256":"b4d5004fb32eefb31012db6f8a2330e89cb769ff498911f8fc06c683c8e46fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4d5004fb32eefb31012db6f8a2330e89cb769ff498911f8fc06c683c8e46fdb","first_computed_at":"2026-07-05T10:41:50.623345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:50.623345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eg9qBDk5DuzHYL5AiPg+4GOBVuIAsKKGWbVCMaIh/j0/Oz+HTulUnvuSq/+mzLrTSQSTPLLKeATObnGXFBa8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:50.623849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:644c4364c9ecc6854be797d3509f9e1ebf3eef59cad5173f0c003cfd89ad3368","sha256:1c134f2fbae6188e9505b6de5bfbb2852875ba1ba05517b36aa40e627eb8083e"],"state_sha256":"d3b8f87cbf6d563aed4e6515912754490b23a442d82635fcfe2f0cb80c287c99"}