{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XCYCZEAFRJ225HBWZWGMBCERN5","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":"cd3fc319bbd971428dda16d85613b8bf653beb3359fc143cb1edf96b67f8bd66","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:09Z","title_canon_sha256":"e9a219a6fb41ca92755a16caff40e8dee298302fbc2ae7f1b661d25c1378b53e"},"schema_version":"1.0","source":{"id":"2403.16998","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16998","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16998v5","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16998","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"XCYCZEAFRJ22","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"XCYCZEAFRJ225HBW","created_at":"2026-07-05T11:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"XCYCZEAF","created_at":"2026-07-05T11:19:48Z"}],"graph_snapshots":[{"event_id":"sha256:f70184b0e8110f4736b8384c97969033e308a64c9ae1f82acff927182d1b5ca4","target":"graph","created_at":"2026-07-05T11:19:48Z","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/2403.16998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs influence this strong performance. Surprisingly, we discover that LLM-based approaches can yield surprisingly good accuracy on long-video tasks with limited video information, sometimes even with no video specific information. Building on this, we explore injecting video-specific information into an LLM-based framework. We utilize off-the-shelf vision tools to ex","authors_text":"Kanchana Ranasinghe, Kumara Kahatapitiya, Michael S. Ryoo, Xiang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:09Z","title":"Understanding Long Videos with Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16998","kind":"arxiv","version":5},"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":"sha256:29b05634c0a5a0f9a1dcb964c0496a4a0e38ea7ffbf87d1793111f65abf206ed","target":"record","created_at":"2026-07-05T11:19:48Z","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":"cd3fc319bbd971428dda16d85613b8bf653beb3359fc143cb1edf96b67f8bd66","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:09Z","title_canon_sha256":"e9a219a6fb41ca92755a16caff40e8dee298302fbc2ae7f1b661d25c1378b53e"},"schema_version":"1.0","source":{"id":"2403.16998","kind":"arxiv","version":5}},"canonical_sha256":"b8b02c90058a75ae9c36cd8cc088916f77f790e8bb1d67b88762a657acc84b44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8b02c90058a75ae9c36cd8cc088916f77f790e8bb1d67b88762a657acc84b44","first_computed_at":"2026-07-05T11:19:48.550358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:48.550358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K4VkEGoZZNkbYOAp4FYJNDg+Zhbc1mk6bLlsLH/lxIZwy+qmSkv1iKupeolXDU6Fk05vAsrk3lVdPr4rQPFHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:48.550795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16998","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29b05634c0a5a0f9a1dcb964c0496a4a0e38ea7ffbf87d1793111f65abf206ed","sha256:f70184b0e8110f4736b8384c97969033e308a64c9ae1f82acff927182d1b5ca4"],"state_sha256":"1f4df40a71c04911825e16a76ed3f2b371730d994201091bfa7a4fe121d3dedf"}