{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DSK4GLYYLL43WMFTKVYL4DYX3N","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":"f1ff2fc2bcc5834daf9dd7c484d07aed7f549926915a71e58a62cf696bbec4d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T17:57:32Z","title_canon_sha256":"75485d9099f364cfeb04d6ab3c8b1d029d8b3f555d9240b456cb70405e56d872"},"schema_version":"1.0","source":{"id":"2503.09590","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09590","created_at":"2026-07-05T10:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09590v2","created_at":"2026-07-05T10:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09590","created_at":"2026-07-05T10:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"DSK4GLYYLL43","created_at":"2026-07-05T10:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"DSK4GLYYLL43WMFT","created_at":"2026-07-05T10:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"DSK4GLYY","created_at":"2026-07-05T10:30:34Z"}],"graph_snapshots":[{"event_id":"sha256:cc1b9f430a938c50d65922b1d6ddec389e024d6f3c0dd122fac0d054aa49da7f","target":"graph","created_at":"2026-07-05T10:30:34Z","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/2503.09590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VQA) in long videos poses the key challenge of extracting relevant information and modeling long-range dependencies from many redundant frames. The self-attention mechanism provides a general solution for sequence modeling, but it has a prohibitive cost when applied to a massive number of spatiotemporal tokens in long videos. Most prior methods rely on compression strategies to lower the computational cost, such as reducing the input length via sparse frame sampling or compressing the output sequence passed to the large language model (LLM) via space-time pooling. How","authors_text":"Gedas Bertasius, Huiyu Wang, Lorenzo Torresani, Md Mohaiminul Islam, Tushar Nagarajan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T17:57:32Z","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09590","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":"sha256:257c518685e219c00e3891665ae36ff16617eb00f41bb0644444fd90836c5a70","target":"record","created_at":"2026-07-05T10:30:34Z","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":"f1ff2fc2bcc5834daf9dd7c484d07aed7f549926915a71e58a62cf696bbec4d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T17:57:32Z","title_canon_sha256":"75485d9099f364cfeb04d6ab3c8b1d029d8b3f555d9240b456cb70405e56d872"},"schema_version":"1.0","source":{"id":"2503.09590","kind":"arxiv","version":2}},"canonical_sha256":"1c95c32f185af9bb30b35570be0f17db68a191f57bb929d25590d61477dfe344","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c95c32f185af9bb30b35570be0f17db68a191f57bb929d25590d61477dfe344","first_computed_at":"2026-07-05T10:30:34.266419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:34.266419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HVRE29phks4p2bJCuhsUdRT5KCeP5MpsGqgJTe0rE1HsP6ZMeEJMCLoDv4Nvlfu/48r3U6kqnX784tOwszstBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:34.266901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09590","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257c518685e219c00e3891665ae36ff16617eb00f41bb0644444fd90836c5a70","sha256:cc1b9f430a938c50d65922b1d6ddec389e024d6f3c0dd122fac0d054aa49da7f"],"state_sha256":"f4e3c7dcdb4b9dd72619511b930266e2a33f7de0e5e9cb91e809932d5ae134cc"}