{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OT53LJ3ZNWR3JVDN2MBRB4OGKA","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":"bf693a29bf15a1466c7034658d81b5454456113b024cbddf7aef2548b7767f74","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T15:15:36Z","title_canon_sha256":"7a9957a722a8a395be1f401e7cbfe7984072f79c5bddf7b3fc72fe1131f5a6b3"},"schema_version":"1.0","source":{"id":"2510.01009","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01009","created_at":"2026-06-02T02:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01009v3","created_at":"2026-06-02T02:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01009","created_at":"2026-06-02T02:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"OT53LJ3ZNWR3","created_at":"2026-06-02T02:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"OT53LJ3ZNWR3JVDN","created_at":"2026-06-02T02:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"OT53LJ3Z","created_at":"2026-06-02T02:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:2c3a33e80942f1765d7e2343eaddc078f23110a4675cfcf4223bfebbb62a6c2d","target":"graph","created_at":"2026-06-02T02:04:09Z","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/2510.01009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-video multimodal question answering requires structured reasoning over visual evidence and dialogue, but Large Vision-Language Models (LVLMs) are constrained by context-window and compute limits. We propose POVQA, which compresses each second into a temporally pooled image (1 fps pooled images) to maintain dense temporal coverage under a fixed token budget. We then train Qwen2.5-VL-7B with supervised fine-tuning (SFT) on rationale+answer targets, and optionally apply Direct Preference Optimization (DPO) for preference alignment. We introduce ReasonVQA as a pilot diagnostic dataset with 12","authors_text":"Ankit Ghimire, Ashim Dahal, Nick Rahimi, Saydul Akbar Murad","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T15:15:36Z","title":"POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01009","kind":"arxiv","version":3},"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":"sha256:0079822eaee8278128eaae04f603ae9a9c94698c37ff43382b33cd7bff5cbc84","target":"record","created_at":"2026-06-02T02:04:09Z","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":"bf693a29bf15a1466c7034658d81b5454456113b024cbddf7aef2548b7767f74","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T15:15:36Z","title_canon_sha256":"7a9957a722a8a395be1f401e7cbfe7984072f79c5bddf7b3fc72fe1131f5a6b3"},"schema_version":"1.0","source":{"id":"2510.01009","kind":"arxiv","version":3}},"canonical_sha256":"74fbb5a7796da3b4d46dd30310f1c6503ad650075c02be55c89c34e2cc56caf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74fbb5a7796da3b4d46dd30310f1c6503ad650075c02be55c89c34e2cc56caf9","first_computed_at":"2026-06-02T02:04:09.505625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:09.505625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfKbA02uUPLGJ8L7d4LheU+3Tk0a9+dGrDz/RVuxzUnF2U09E1rd4sut4M28YK78IZHDhbXUTPc2Kay9F1NbCg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:09.506138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01009","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0079822eaee8278128eaae04f603ae9a9c94698c37ff43382b33cd7bff5cbc84","sha256:2c3a33e80942f1765d7e2343eaddc078f23110a4675cfcf4223bfebbb62a6c2d"],"state_sha256":"fb36fb44ff3a8031a0c4725128c4f0e3062bb5c627fb22cc9c8137cb045e7920"}