{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7JSIKZ5HNYMVEEYVMGRXFAIXF","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":"846321f956fc09ecde19c21359fe97233dd8f6fb3917219a9c4ef77cdfdcad58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T18:33:04Z","title_canon_sha256":"b652313124559341886d34e817d822733a2570ad7b710e8af9688125d6afdc6d"},"schema_version":"1.0","source":{"id":"2404.04346","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04346","created_at":"2026-07-05T08:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04346v3","created_at":"2026-07-05T08:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04346","created_at":"2026-07-05T08:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"R7JSIKZ5HNYM","created_at":"2026-07-05T08:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"R7JSIKZ5HNYMVEEY","created_at":"2026-07-05T08:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"R7JSIKZ5","created_at":"2026-07-05T08:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:1fa3c4fe8f392841a94d8c5d53a611434c1364c80cdf7bdbf2fc5450dbbb7bfe","target":"graph","created_at":"2026-07-05T08:15:12Z","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/2404.04346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution due to their demonstrated emergent capabilities on new tasks. However, despite being trained on millions of short seconds-long videos, vLLMs are unable to understand minutes-long videos and accurately answer questions about them. To address this limitation, we propose a lightweight and self-supervised approach, Key frame-conditioned long video-LLM (Koala), ","authors_text":"Bryan A. Plummer, Bryan Russell, Hanieh Deilamsalehy, Jui-Hsien Wang, Kate Saenko, Ping Hu, Reuben Tan, Ximeng Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T18:33:04Z","title":"Koala: Key frame-conditioned long video-LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04346","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":"sha256:88dbc47e9ab06e11c495e9060c7c60712f82676f28a7d857e990de975be4e426","target":"record","created_at":"2026-07-05T08:15:12Z","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":"846321f956fc09ecde19c21359fe97233dd8f6fb3917219a9c4ef77cdfdcad58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T18:33:04Z","title_canon_sha256":"b652313124559341886d34e817d822733a2570ad7b710e8af9688125d6afdc6d"},"schema_version":"1.0","source":{"id":"2404.04346","kind":"arxiv","version":3}},"canonical_sha256":"8fd3242b3d3b70ca9098ab0d1b9408b974a605e5eb28e1dc72f09b445dc344f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fd3242b3d3b70ca9098ab0d1b9408b974a605e5eb28e1dc72f09b445dc344f2","first_computed_at":"2026-07-05T08:15:12.777835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:12.777835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LOFNq73A/4fBfyXlVr4PRAjSZjPgv8bfiO718P66cxg/voZMXmEt0VI1ocVlvcToFkHnC3Y1X6VJuIHeLskMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:12.778297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04346","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88dbc47e9ab06e11c495e9060c7c60712f82676f28a7d857e990de975be4e426","sha256:1fa3c4fe8f392841a94d8c5d53a611434c1364c80cdf7bdbf2fc5450dbbb7bfe"],"state_sha256":"90922142e55f14cc8b2c0576a7f261d6d890575fc6c89eaf1171847077bbf63c"}