{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CH7LJ3ZFFMLCIRYQRV2LRIX7WF","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":"1ea29c08256ad9e2d0408ac7233fb0cbe7901aba364a1143f3b219d884bde732","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T18:59:27Z","title_canon_sha256":"cb59bbc3c2c8b29eeedd0f5db2db1f8282d34220a7c9e8c83555b9d67d5dff83"},"schema_version":"1.0","source":{"id":"2512.16978","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.16978","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2512.16978v2","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16978","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"CH7LJ3ZFFMLC","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"CH7LJ3ZFFMLCIRYQ","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"CH7LJ3ZF","created_at":"2026-06-19T16:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:1c0621469235af8b90d6f712b87f3639a342bdba31ac356b8ba14654654bcdc2","target":"graph","created_at":"2026-06-19T16:10:33Z","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/2512.16978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form omni-modal video understanding requires integrating vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce LongShOTBench, a long video understanding benchmark designed around three coupled goals: holistic omni-modal integration, intent-driven open-ended interaction, and rubric-level diagnosis. It builds single- and multi-turn questions from real viewing scenarios, with systematic tasks probing visual, speech","authors_text":"Beknur Kalmakhanbet, Fahad Shahbaz Khan, Hisham Cholakkal, Jaseel Muhammad Kaithakkodan, Jean Lahoud, Jinxing Zhou, Mariette Awad, Mohammad Almansoori, Mohammed Irfan Kurpath, Noor Ahsan, Rao Muhammad Anwer, Rishabh Lalla, Sahal Shaji Mullappilly, Salman Khan, Sambal Shikhar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T18:59:27Z","title":"A Benchmark for Omni-Modal Reasoning in Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.16978","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":"sha256:7da634bad42a4541db756917f46ffe0d9c810355c5159ef76ae766ca8a4fcd2a","target":"record","created_at":"2026-06-19T16:10:33Z","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":"1ea29c08256ad9e2d0408ac7233fb0cbe7901aba364a1143f3b219d884bde732","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T18:59:27Z","title_canon_sha256":"cb59bbc3c2c8b29eeedd0f5db2db1f8282d34220a7c9e8c83555b9d67d5dff83"},"schema_version":"1.0","source":{"id":"2512.16978","kind":"arxiv","version":2}},"canonical_sha256":"11feb4ef252b162447108d74b8a2ffb152f450a3cbd0e080bb1540a2643cab09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11feb4ef252b162447108d74b8a2ffb152f450a3cbd0e080bb1540a2643cab09","first_computed_at":"2026-06-19T16:10:33.762353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:33.762353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iONvnBwmzjH7xiqbmzdc4feLQqN3eSRg1k0W+YtT3quJUx02uwvkjqpTR6fSDuc7G9T0gkjMyldpGqxyjS0Dw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:33.762784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.16978","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7da634bad42a4541db756917f46ffe0d9c810355c5159ef76ae766ca8a4fcd2a","sha256:1c0621469235af8b90d6f712b87f3639a342bdba31ac356b8ba14654654bcdc2"],"state_sha256":"7d676e905ed25aa26a039d8d6efdd30c1631499a5976d84846121adf73140e37"}