{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y34LWIMX7VG6GP2KE2TMUGS5MO","short_pith_number":"pith:Y34LWIMX","schema_version":"1.0","canonical_sha256":"c6f8bb2197fd4de33f4a26a6ca1a5d63866b0c918ba23810b8b0843a1960db97","source":{"kind":"arxiv","id":"2603.29943","version":2},"attestation_state":"computed","paper":{"title":"Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumihiko Tsuchiya, Mahiro Ukai, Nakamasa Inoue, Shuhei Kurita, Shunsuke Yasuki, Taiki Miyanishi, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2026-03-31T16:16:17Z","abstract_excerpt":"Final-answer video QA can show whether a model predicts the right number, but not which instances it counted, when the supporting evidence occurs, or why it failed. We diagnose long-video quantitative reasoning in multimodal large language models (MLLMs) through three coupled abilities: enumerating query-relevant instances, temporally grounding supporting evidence, and aggregating the evidence into counts. To support this analysis, we build EC-Bench, an evidence-annotated evaluation suite with 152 untrimmed videos longer than 30 minutes, 1,699 open-ended queries across six reasoning categories"},"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":"2603.29943","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-31T16:16:17Z","cross_cats_sorted":[],"title_canon_sha256":"e7d652964540abfb8f21e4720d57c4b4c0939d7311dab2b9f8b44865147ebb22","abstract_canon_sha256":"4de321f6dc0f025a23aed6ec01d92fab954a21f5947eb8cff855bc1dad00e20d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:07.883394Z","signature_b64":"8c5VNlm6+mcgIxsoGuvmrz72gtg7OZGBUhUlysC61CbwBSkJNvvZwtXYkVaOVlbSnqHn2LYhFpETFlZ+mVG5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6f8bb2197fd4de33f4a26a6ca1a5d63866b0c918ba23810b8b0843a1960db97","last_reissued_at":"2026-07-13T01:20:07.881836Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:07.881836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumihiko Tsuchiya, Mahiro Ukai, Nakamasa Inoue, Shuhei Kurita, Shunsuke Yasuki, Taiki Miyanishi, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2026-03-31T16:16:17Z","abstract_excerpt":"Final-answer video QA can show whether a model predicts the right number, but not which instances it counted, when the supporting evidence occurs, or why it failed. We diagnose long-video quantitative reasoning in multimodal large language models (MLLMs) through three coupled abilities: enumerating query-relevant instances, temporally grounding supporting evidence, and aggregating the evidence into counts. To support this analysis, we build EC-Bench, an evidence-annotated evaluation suite with 152 untrimmed videos longer than 30 minutes, 1,699 open-ended queries across six reasoning categories"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29943","kind":"arxiv","version":2},"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/2603.29943/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":"2603.29943","created_at":"2026-07-13T01:20:07.882605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29943v2","created_at":"2026-07-13T01:20:07.882605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29943","created_at":"2026-07-13T01:20:07.882605+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y34LWIMX7VG6","created_at":"2026-07-13T01:20:07.882605+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y34LWIMX7VG6GP2K","created_at":"2026-07-13T01:20:07.882605+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y34LWIMX","created_at":"2026-07-13T01:20:07.882605+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/Y34LWIMX7VG6GP2KE2TMUGS5MO","json":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO.json","graph_json":"https://pith.science/api/pith-number/Y34LWIMX7VG6GP2KE2TMUGS5MO/graph.json","events_json":"https://pith.science/api/pith-number/Y34LWIMX7VG6GP2KE2TMUGS5MO/events.json","paper":"https://pith.science/paper/Y34LWIMX"},"agent_actions":{"view_html":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO","download_json":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO.json","view_paper":"https://pith.science/paper/Y34LWIMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29943&json=true","fetch_graph":"https://pith.science/api/pith-number/Y34LWIMX7VG6GP2KE2TMUGS5MO/graph.json","fetch_events":"https://pith.science/api/pith-number/Y34LWIMX7VG6GP2KE2TMUGS5MO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO/action/storage_attestation","attest_author":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO/action/author_attestation","sign_citation":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO/action/citation_signature","submit_replication":"https://pith.science/pith/Y34LWIMX7VG6GP2KE2TMUGS5MO/action/replication_record"}},"created_at":"2026-07-13T01:20:07.882605+00:00","updated_at":"2026-07-13T01:20:07.882605+00:00"}