{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JB3CDBRMZYCEPBYS23WUZECDNV","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":"5fe858ad3780150441110c03a22a32362265e8ae1cc5fd14a7a64a2680834b32","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T03:41:13Z","title_canon_sha256":"cb54e2a1363efe225b964539cbf486005367cc8f5b26f3574743aad42f26f3d0"},"schema_version":"1.0","source":{"id":"2204.02566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02566","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02566v1","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02566","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"JB3CDBRMZYCE","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"JB3CDBRMZYCEPBYS","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"JB3CDBRM","created_at":"2026-07-05T04:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:432fdeeaf8bb4e0581636181d560f9ccb28d4dacfeb1e2066b322c8da721c6ad","target":"graph","created_at":"2026-07-05T04:12:10Z","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/2204.02566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Procedural Multimodal Documents (PMDs) organize textual instructions and corresponding images step by step. Comprehending PMDs and inducing their representations for the downstream reasoning tasks is designated as Procedural MultiModal Machine Comprehension (M3C). In this study, we approach Procedural M3C at a fine-grained level (compared with existing explorations at a document or sentence level), that is, entity. With delicate consideration, we model entity both in its temporal and cross-modal relation and propose a novel Temporal-Modal Entity Graph (TMEG). Specifically, graph structure is f","authors_text":"Huibin Zhang, Jun Wang, Ning Jiang, Xin Wei, Yao Zhang, Yufan Li, Zhengkun Zhang, Zhenglu Yang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T03:41:13Z","title":"Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02566","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:cf4c548ee4ec465bf34b1f5a117482c735f4df1ce0516fbd748a6138c226704e","target":"record","created_at":"2026-07-05T04:12:10Z","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":"5fe858ad3780150441110c03a22a32362265e8ae1cc5fd14a7a64a2680834b32","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T03:41:13Z","title_canon_sha256":"cb54e2a1363efe225b964539cbf486005367cc8f5b26f3574743aad42f26f3d0"},"schema_version":"1.0","source":{"id":"2204.02566","kind":"arxiv","version":1}},"canonical_sha256":"487621862cce04478712d6ed4c90436d6c33d9202a83c5ae0befdb55db3fb7a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487621862cce04478712d6ed4c90436d6c33d9202a83c5ae0befdb55db3fb7a0","first_computed_at":"2026-07-05T04:12:10.158759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:10.158759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChVmIrWFyY4f5aUX/jg8hkMsiB5TBG+9Zse8pcuME3VTRRYM/CB3KrkpR8ZTre6hat5dmzry2vgbR885k4HQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:10.159135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf4c548ee4ec465bf34b1f5a117482c735f4df1ce0516fbd748a6138c226704e","sha256:432fdeeaf8bb4e0581636181d560f9ccb28d4dacfeb1e2066b322c8da721c6ad"],"state_sha256":"f8e58a468b52f7ac198d87a4fae85a451ad93b01b0691a1a65276f9da39e9624"}