{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4EF5OEKPELABTU5XI7MW4ILG2J","short_pith_number":"pith:4EF5OEKP","schema_version":"1.0","canonical_sha256":"e10bd7114f22c019d3b747d96e2166d2408cf2d77f494e2ddc0de536ec53b5b5","source":{"kind":"arxiv","id":"2606.02522","version":1},"attestation_state":"computed","paper":{"title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Cao, Shaofeng Zhang, Xiangyu Zhao, Xiaolin Liu, Xing Sun, Xin Li, Xuehui Wang, Xue Yang, Xu Yang, Yan Li, Yilun Zhu, Zhihang Zhong","submitted_at":"2026-06-01T17:32:20Z","abstract_excerpt":"Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored. Many practical questions are determined by momentary visual events: localized actions or state transitions that may last only a few frames. Such evidence can be skipped by sparse frame sampling, suppressed by visual-token compression, or diluted by coarse temporal aggregation, causing failures that language-side reasoning cannot reliably recover. We introduce Moment-Video, a benchmark for"},"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":"2606.02522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T17:32:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7c5b2dcf0a9f1751baec8fb89e5cf4c36302de719c27db04d262106a2215dde","abstract_canon_sha256":"c681f82cff233870c8e5fec5b7b0ccc3a37aaef8343efab323ddd63d5ec62579"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:08.490629Z","signature_b64":"gvVMQLWle40ozOA7KwkXwz6lXxMY0NOWUzlNvgZkk+K+OUM0FB7Y+E0K33UYQuc1pC/BSIFz8XKmW2XuEzYmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e10bd7114f22c019d3b747d96e2166d2408cf2d77f494e2ddc0de536ec53b5b5","last_reissued_at":"2026-06-02T03:05:08.490213Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:08.490213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Cao, Shaofeng Zhang, Xiangyu Zhao, Xiaolin Liu, Xing Sun, Xin Li, Xuehui Wang, Xue Yang, Xu Yang, Yan Li, Yilun Zhu, Zhihang Zhong","submitted_at":"2026-06-01T17:32:20Z","abstract_excerpt":"Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored. Many practical questions are determined by momentary visual events: localized actions or state transitions that may last only a few frames. Such evidence can be skipped by sparse frame sampling, suppressed by visual-token compression, or diluted by coarse temporal aggregation, causing failures that language-side reasoning cannot reliably recover. We introduce Moment-Video, a benchmark for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02522","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/2606.02522/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":"2606.02522","created_at":"2026-06-02T03:05:08.490269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02522v1","created_at":"2026-06-02T03:05:08.490269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02522","created_at":"2026-06-02T03:05:08.490269+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EF5OEKPELAB","created_at":"2026-06-02T03:05:08.490269+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EF5OEKPELABTU5X","created_at":"2026-06-02T03:05:08.490269+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EF5OEKP","created_at":"2026-06-02T03:05:08.490269+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/4EF5OEKPELABTU5XI7MW4ILG2J","json":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J.json","graph_json":"https://pith.science/api/pith-number/4EF5OEKPELABTU5XI7MW4ILG2J/graph.json","events_json":"https://pith.science/api/pith-number/4EF5OEKPELABTU5XI7MW4ILG2J/events.json","paper":"https://pith.science/paper/4EF5OEKP"},"agent_actions":{"view_html":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J","download_json":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J.json","view_paper":"https://pith.science/paper/4EF5OEKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02522&json=true","fetch_graph":"https://pith.science/api/pith-number/4EF5OEKPELABTU5XI7MW4ILG2J/graph.json","fetch_events":"https://pith.science/api/pith-number/4EF5OEKPELABTU5XI7MW4ILG2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J/action/storage_attestation","attest_author":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J/action/author_attestation","sign_citation":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J/action/citation_signature","submit_replication":"https://pith.science/pith/4EF5OEKPELABTU5XI7MW4ILG2J/action/replication_record"}},"created_at":"2026-06-02T03:05:08.490269+00:00","updated_at":"2026-06-02T03:05:08.490269+00:00"}