{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W7NYHLPELHSSJWZPOVHQ4R3ANO","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":"75ce3b591a8ab85dff48f606c6a43f306555297ad502e350b112ec41e0f817b6","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T16:29:13Z","title_canon_sha256":"fd59efcbac239c05e846651dcf656d49a89600294c7d378ac92be9fb075a41d6"},"schema_version":"1.0","source":{"id":"2606.07433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07433","created_at":"2026-06-08T01:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07433v1","created_at":"2026-06-08T01:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07433","created_at":"2026-06-08T01:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"W7NYHLPELHSS","created_at":"2026-06-08T01:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"W7NYHLPELHSSJWZP","created_at":"2026-06-08T01:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"W7NYHLPE","created_at":"2026-06-08T01:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:079c52558068e21ef244738abc50b38de52aff6830865974f045823d1a634aca","target":"graph","created_at":"2026-06-08T01:05:26Z","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/2606.07433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios. These scenarios require models to handle sparse evidence, long-range dependencies, multimodal alignment, and reliable inference under limited computational budgets. This work presents a human-view perspective on LLM-based video understanding, organized around three functional abilities: watching, remembering, and reasoning. Rather than treating video tasks as isolated benchmarks, this view provides a unifi","authors_text":"Guangliang Cheng, Haochen Wang, Jason Li, Jiahao Meng, Jiangning Zhang, Kuan Gao, Lingdong Kong, Lu Qi, Minghsuan Yang, Qianyu Zhou, Qi Xu, Weisong Liu, Yanwei Li, Yue Tan, Yunhai Tong","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T16:29:13Z","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07433","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:d0878d04f3168f3ebdb48ad485081fb295538be8558df9b4ed4ab3699b83966f","target":"record","created_at":"2026-06-08T01:05:26Z","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":"75ce3b591a8ab85dff48f606c6a43f306555297ad502e350b112ec41e0f817b6","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T16:29:13Z","title_canon_sha256":"fd59efcbac239c05e846651dcf656d49a89600294c7d378ac92be9fb075a41d6"},"schema_version":"1.0","source":{"id":"2606.07433","kind":"arxiv","version":1}},"canonical_sha256":"b7db83ade459e524db2f754f0e47606ba225d248b232fd38f820072c2cbbd15b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7db83ade459e524db2f754f0e47606ba225d248b232fd38f820072c2cbbd15b","first_computed_at":"2026-06-08T01:05:26.853443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:26.853443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iBCXx5O/wdeb5F/iHi5kdpz3bJetNvFzaZ2AgJeEuq1x/uIgUeLAnYK586UJ5c+nt/LaoJN3ov5nQ1pgsL+DAw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:26.853863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0878d04f3168f3ebdb48ad485081fb295538be8558df9b4ed4ab3699b83966f","sha256:079c52558068e21ef244738abc50b38de52aff6830865974f045823d1a634aca"],"state_sha256":"1c678e63e352264cfb4da85f201b4697c4977aa5fd36ec949fa402b12cbaf8ec"}