{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YR2MJWX2ZZTNR34FQUJT4UBWSE","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":"852cdaddb0c2045229397f5e14fb21cb458b992c098db2895f854af2117f0734","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T13:18:40Z","title_canon_sha256":"5a51bd00b66161321df12a74a94a6534edd070053ca8c6a84298189141eb3d69"},"schema_version":"1.0","source":{"id":"2503.21483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21483","created_at":"2026-07-05T10:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21483v1","created_at":"2026-07-05T10:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21483","created_at":"2026-07-05T10:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"YR2MJWX2ZZTN","created_at":"2026-07-05T10:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"YR2MJWX2ZZTNR34F","created_at":"2026-07-05T10:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"YR2MJWX2","created_at":"2026-07-05T10:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:2cc1e12b751b871ffab94583d236b4e4510792f3108d851c872bccafc90a9c22","target":"graph","created_at":"2026-07-05T10:40:26Z","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/2503.21483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large video-language models (VLMs) have demonstrated promising progress in various video understanding tasks. However, their effectiveness in long-form video analysis is constrained by limited context windows. Traditional approaches, such as uniform frame sampling, often inevitably allocate resources to irrelevant content, diminishing their effectiveness in real-world scenarios. In this paper, we introduce BOLT, a method to BOost Large VLMs without additional Training through a comprehensive study of frame selection strategies. First, to enable a more realistic evaluation of VLMs in long-form ","authors_text":"Bernard Ghanem, Chen Zhao, Shuming Liu, Tianqi Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T13:18:40Z","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21483","kind":"arxiv","version":1},"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":"sha256:991719326142307e4919bf7456aaad6b71a3f7973569061e866d016ecedcf8b5","target":"record","created_at":"2026-07-05T10:40:26Z","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":"852cdaddb0c2045229397f5e14fb21cb458b992c098db2895f854af2117f0734","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T13:18:40Z","title_canon_sha256":"5a51bd00b66161321df12a74a94a6534edd070053ca8c6a84298189141eb3d69"},"schema_version":"1.0","source":{"id":"2503.21483","kind":"arxiv","version":1}},"canonical_sha256":"c474c4daface66d8ef8585133e503691051c54155a8b7aa8e7afec03ba2d6945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c474c4daface66d8ef8585133e503691051c54155a8b7aa8e7afec03ba2d6945","first_computed_at":"2026-07-05T10:40:26.133624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:26.133624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uae7atSYIY4wO+JfIAHCr5IzG/qZcS+wqSt5sTeAKvmep1oVhPwhnX20za1GKfppDsiMA0oXl+WlzUG6uD1VAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:26.134108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:991719326142307e4919bf7456aaad6b71a3f7973569061e866d016ecedcf8b5","sha256:2cc1e12b751b871ffab94583d236b4e4510792f3108d851c872bccafc90a9c22"],"state_sha256":"2e91057d1aacbf129dd92e8458522d5204142a59eb2cf57d05b81b7ca481bfaf"}