{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y34LWIMX7VG6GP2KE2TMUGS5MO","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":"4de321f6dc0f025a23aed6ec01d92fab954a21f5947eb8cff855bc1dad00e20d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-31T16:16:17Z","title_canon_sha256":"e7d652964540abfb8f21e4720d57c4b4c0939d7311dab2b9f8b44865147ebb22"},"schema_version":"1.0","source":{"id":"2603.29943","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29943","created_at":"2026-07-13T01:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29943v2","created_at":"2026-07-13T01:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29943","created_at":"2026-07-13T01:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"Y34LWIMX7VG6","created_at":"2026-07-13T01:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"Y34LWIMX7VG6GP2K","created_at":"2026-07-13T01:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"Y34LWIMX","created_at":"2026-07-13T01:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:1bf2fbf4b9f93dda8c5f2c5d2f5d123ac313464688d8bd9b7d817caffe1c8503","target":"graph","created_at":"2026-07-13T01:20:07Z","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/2603.29943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fumihiko Tsuchiya, Mahiro Ukai, Nakamasa Inoue, Shuhei Kurita, Shunsuke Yasuki, Taiki Miyanishi, Yusuke Iwasawa, Yutaka Matsuo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-31T16:16:17Z","title":"Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29943","kind":"arxiv","version":2},"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":"sha256:68ba222d8f42f24f3b244c07034e74e3500316f850df299b36757d7659439c3f","target":"record","created_at":"2026-07-13T01:20:07Z","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":"4de321f6dc0f025a23aed6ec01d92fab954a21f5947eb8cff855bc1dad00e20d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-31T16:16:17Z","title_canon_sha256":"e7d652964540abfb8f21e4720d57c4b4c0939d7311dab2b9f8b44865147ebb22"},"schema_version":"1.0","source":{"id":"2603.29943","kind":"arxiv","version":2}},"canonical_sha256":"c6f8bb2197fd4de33f4a26a6ca1a5d63866b0c918ba23810b8b0843a1960db97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f8bb2197fd4de33f4a26a6ca1a5d63866b0c918ba23810b8b0843a1960db97","first_computed_at":"2026-07-13T01:20:07.881836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:20:07.881836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8c5VNlm6+mcgIxsoGuvmrz72gtg7OZGBUhUlysC61CbwBSkJNvvZwtXYkVaOVlbSnqHn2LYhFpETFlZ+mVG5Aw==","signature_status":"signed_v1","signed_at":"2026-07-13T01:20:07.883394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29943","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68ba222d8f42f24f3b244c07034e74e3500316f850df299b36757d7659439c3f","sha256:1bf2fbf4b9f93dda8c5f2c5d2f5d123ac313464688d8bd9b7d817caffe1c8503"],"state_sha256":"621692db691aa51c249484780685f9232e286b1bdd4452d5c90bf00b40feaf73"}