{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W7NYHLPELHSSJWZPOVHQ4R3ANO","short_pith_number":"pith:W7NYHLPE","schema_version":"1.0","canonical_sha256":"b7db83ade459e524db2f754f0e47606ba225d248b232fd38f820072c2cbbd15b","source":{"kind":"arxiv","id":"2606.07433","version":1},"attestation_state":"computed","paper":{"title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","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","submitted_at":"2026-06-05T16:29:13Z","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"},"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":"2606.07433","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T16:29:13Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"fd59efcbac239c05e846651dcf656d49a89600294c7d378ac92be9fb075a41d6","abstract_canon_sha256":"75ce3b591a8ab85dff48f606c6a43f306555297ad502e350b112ec41e0f817b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:26.853863Z","signature_b64":"iBCXx5O/wdeb5F/iHi5kdpz3bJetNvFzaZ2AgJeEuq1x/uIgUeLAnYK586UJ5c+nt/LaoJN3ov5nQ1pgsL+DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7db83ade459e524db2f754f0e47606ba225d248b232fd38f820072c2cbbd15b","last_reissued_at":"2026-06-08T01:05:26.853443Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:26.853443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","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","submitted_at":"2026-06-05T16:29:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07433","kind":"arxiv","version":1},"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/2606.07433/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":"2606.07433","created_at":"2026-06-08T01:05:26.853502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07433v1","created_at":"2026-06-08T01:05:26.853502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07433","created_at":"2026-06-08T01:05:26.853502+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7NYHLPELHSS","created_at":"2026-06-08T01:05:26.853502+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7NYHLPELHSSJWZP","created_at":"2026-06-08T01:05:26.853502+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7NYHLPE","created_at":"2026-06-08T01:05:26.853502+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/W7NYHLPELHSSJWZPOVHQ4R3ANO","json":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO.json","graph_json":"https://pith.science/api/pith-number/W7NYHLPELHSSJWZPOVHQ4R3ANO/graph.json","events_json":"https://pith.science/api/pith-number/W7NYHLPELHSSJWZPOVHQ4R3ANO/events.json","paper":"https://pith.science/paper/W7NYHLPE"},"agent_actions":{"view_html":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO","download_json":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO.json","view_paper":"https://pith.science/paper/W7NYHLPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07433&json=true","fetch_graph":"https://pith.science/api/pith-number/W7NYHLPELHSSJWZPOVHQ4R3ANO/graph.json","fetch_events":"https://pith.science/api/pith-number/W7NYHLPELHSSJWZPOVHQ4R3ANO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO/action/storage_attestation","attest_author":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO/action/author_attestation","sign_citation":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO/action/citation_signature","submit_replication":"https://pith.science/pith/W7NYHLPELHSSJWZPOVHQ4R3ANO/action/replication_record"}},"created_at":"2026-06-08T01:05:26.853502+00:00","updated_at":"2026-06-08T01:05:26.853502+00:00"}