{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZE5KO7FXMGDYQ3PWCM3QVZMB4N","short_pith_number":"pith:ZE5KO7FX","canonical_record":{"source":{"id":"2605.09223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T23:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"f08d9475c9e83d2c91ec7e41d3b77914c3a95f89ded01af82ac795f1f3db8be3","abstract_canon_sha256":"d863c7aadb433fee407c9e3456890859a9a3da125c5dcb4e71ab9e70fcbed22c"},"schema_version":"1.0"},"canonical_sha256":"c93aa77cb76187886df613370ae581e3417d62bc861ace582ed2bd96d4983511","source":{"kind":"arxiv","id":"2605.09223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09223","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09223v2","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09223","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZE5KO7FXMGDY","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZE5KO7FXMGDYQ3PW","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZE5KO7FX","created_at":"2026-05-26T02:04:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZE5KO7FXMGDYQ3PWCM3QVZMB4N","target":"record","payload":{"canonical_record":{"source":{"id":"2605.09223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T23:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"f08d9475c9e83d2c91ec7e41d3b77914c3a95f89ded01af82ac795f1f3db8be3","abstract_canon_sha256":"d863c7aadb433fee407c9e3456890859a9a3da125c5dcb4e71ab9e70fcbed22c"},"schema_version":"1.0"},"canonical_sha256":"c93aa77cb76187886df613370ae581e3417d62bc861ace582ed2bd96d4983511","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:12.609544Z","signature_b64":"rAYCIqg4P7kiBSXj+fbEdR7agWDMNJ62yBOVfRcSlYEjSoYzN6TWsOBXDr1q8vYxFTooZyV1gyLsLjKo0hh2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93aa77cb76187886df613370ae581e3417d62bc861ace582ed2bd96d4983511","last_reissued_at":"2026-05-26T02:04:12.608900Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:12.608900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.09223","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aabtzAfXDpfVcJw6jyVEp4OZOt7j+a0u2UjL/J3hEExYdzsIiCQfd7V8uzbbrV1oNvaq1uTpWviutZF8+68cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:18:13.893548Z"},"content_sha256":"7ee10ba24de33c9586e01760096c75656547590c8daf73f733e192e1da87acf4","schema_version":"1.0","event_id":"sha256:7ee10ba24de33c9586e01760096c75656547590c8daf73f733e192e1da87acf4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZE5KO7FXMGDYQ3PWCM3QVZMB4N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CATS selects long-video frames by tracking curvature in query-relevance scores over time.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdul Mohaimen Al Radi, Ismat Rahman, Md Mosaddek Khan, Md. Tanvir Alam, Mehrajul Abadin Miraj, Shariful Islam Rayhan, Yu Tian","submitted_at":"2026-05-09T23:47:46Z","abstract_excerpt":"Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through multi stage retrieval pipelines with substantial preprocessing cost. We propose \\textbf{CREST}, a training-free frame selection method grounded in the temporal geometry of query--frame relevance. CREST is based on the observation that relevance over time exhibits structured local variation: sharp curvature around salient events and flatter regions in redundant segments. By using l"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under a fixed backbone and frame budget, CATS consistently outperforms prior lightweight approaches such as AKS on LongVideoBench and VideoMME. CATS retains approximately 93-95% of MIRA's performance while requiring only 3-4% of its preprocessing cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That curvature of query-frame relevance scores reliably identifies salient events and surrounding context across diverse video domains without systematic omission of critical information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CATS selects long-video frames by tracking curvature in query-relevance scores over time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e19d20be28c3efd511d6805af14f701fd424f3fb3ff0a6039bf3c0ce696666a6"},"source":{"id":"2605.09223","kind":"arxiv","version":2},"verdict":{"id":"5ca6f1b6-8978-4034-80c7-aa316c050218","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:02:55.452855Z","strongest_claim":"Under a fixed backbone and frame budget, CATS consistently outperforms prior lightweight approaches such as AKS on LongVideoBench and VideoMME. CATS retains approximately 93-95% of MIRA's performance while requiring only 3-4% of its preprocessing cost.","one_line_summary":"CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That curvature of query-frame relevance scores reliably identifies salient events and surrounding context across diverse video domains without systematic omission of critical information.","pith_extraction_headline":"CATS selects long-video frames by tracking curvature in query-relevance scores over time."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09223/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T08:02:09.568722Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T20:35:05.307347Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T13:31:18.149097Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:27:51.775941Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d678533d0540d0dfb1fd734efc217246561df29928c3513fd601e3085b44d08a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5ca6f1b6-8978-4034-80c7-aa316c050218"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ze83ea9ImF5MpiTnjW3kNTCbIid9rorWuaimoozYuixSuExXaVbpbjb/a8Pc20ib6mh+vsaqUkjEAZC/F3ZUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:18:13.894260Z"},"content_sha256":"40656ae7deae7acbc81f5bac46c351e9b1e975cd47c3ad9f47c3f46d5584f835","schema_version":"1.0","event_id":"sha256:40656ae7deae7acbc81f5bac46c351e9b1e975cd47c3ad9f47c3f46d5584f835"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/bundle.json","state_url":"https://pith.science/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T08:18:13Z","links":{"resolver":"https://pith.science/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N","bundle":"https://pith.science/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/bundle.json","state":"https://pith.science/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZE5KO7FXMGDYQ3PWCM3QVZMB4N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZE5KO7FXMGDYQ3PWCM3QVZMB4N","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":"d863c7aadb433fee407c9e3456890859a9a3da125c5dcb4e71ab9e70fcbed22c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T23:47:46Z","title_canon_sha256":"f08d9475c9e83d2c91ec7e41d3b77914c3a95f89ded01af82ac795f1f3db8be3"},"schema_version":"1.0","source":{"id":"2605.09223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09223","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09223v2","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09223","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZE5KO7FXMGDY","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZE5KO7FXMGDYQ3PW","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZE5KO7FX","created_at":"2026-05-26T02:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:40656ae7deae7acbc81f5bac46c351e9b1e975cd47c3ad9f47c3f46d5584f835","target":"graph","created_at":"2026-05-26T02:04:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Under a fixed backbone and frame budget, CATS consistently outperforms prior lightweight approaches such as AKS on LongVideoBench and VideoMME. CATS retains approximately 93-95% of MIRA's performance while requiring only 3-4% of its preprocessing cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That curvature of query-frame relevance scores reliably identifies salient events and surrounding context across diverse video domains without systematic omission of critical information."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CATS selects long-video frames by tracking curvature in query-relevance scores over time."}],"snapshot_sha256":"e19d20be28c3efd511d6805af14f701fd424f3fb3ff0a6039bf3c0ce696666a6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T08:02:09.568722Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T20:35:05.307347Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T13:31:18.149097Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T10:27:51.775941Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.09223/integrity.json","findings":[],"snapshot_sha256":"d678533d0540d0dfb1fd734efc217246561df29928c3513fd601e3085b44d08a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through multi stage retrieval pipelines with substantial preprocessing cost. We propose \\textbf{CREST}, a training-free frame selection method grounded in the temporal geometry of query--frame relevance. CREST is based on the observation that relevance over time exhibits structured local variation: sharp curvature around salient events and flatter regions in redundant segments. By using l","authors_text":"Abdul Mohaimen Al Radi, Ismat Rahman, Md Mosaddek Khan, Md. Tanvir Alam, Mehrajul Abadin Miraj, Shariful Islam Rayhan, Yu Tian","cross_cats":[],"headline":"CATS selects long-video frames by tracking curvature in query-relevance scores over time.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T23:47:46Z","title":"CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.09223","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T03:02:55.452855Z","id":"5ca6f1b6-8978-4034-80c7-aa316c050218","model_set":{"reader":"grok-4.3"},"one_line_summary":"CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CATS selects long-video frames by tracking curvature in query-relevance scores over time.","strongest_claim":"Under a fixed backbone and frame budget, CATS consistently outperforms prior lightweight approaches such as AKS on LongVideoBench and VideoMME. CATS retains approximately 93-95% of MIRA's performance while requiring only 3-4% of its preprocessing cost.","weakest_assumption":"That curvature of query-frame relevance scores reliably identifies salient events and surrounding context across diverse video domains without systematic omission of critical information."}},"verdict_id":"5ca6f1b6-8978-4034-80c7-aa316c050218"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ee10ba24de33c9586e01760096c75656547590c8daf73f733e192e1da87acf4","target":"record","created_at":"2026-05-26T02:04:12Z","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":"d863c7aadb433fee407c9e3456890859a9a3da125c5dcb4e71ab9e70fcbed22c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T23:47:46Z","title_canon_sha256":"f08d9475c9e83d2c91ec7e41d3b77914c3a95f89ded01af82ac795f1f3db8be3"},"schema_version":"1.0","source":{"id":"2605.09223","kind":"arxiv","version":2}},"canonical_sha256":"c93aa77cb76187886df613370ae581e3417d62bc861ace582ed2bd96d4983511","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c93aa77cb76187886df613370ae581e3417d62bc861ace582ed2bd96d4983511","first_computed_at":"2026-05-26T02:04:12.608900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:12.608900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rAYCIqg4P7kiBSXj+fbEdR7agWDMNJ62yBOVfRcSlYEjSoYzN6TWsOBXDr1q8vYxFTooZyV1gyLsLjKo0hh2CA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:12.609544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ee10ba24de33c9586e01760096c75656547590c8daf73f733e192e1da87acf4","sha256:40656ae7deae7acbc81f5bac46c351e9b1e975cd47c3ad9f47c3f46d5584f835"],"state_sha256":"08f3b548bf42995dd76824d6c6cb0db6cb5fe707536e7bd69729247b5ffcf6b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oNrCWYbo6QhE2iqgdsvdU8aD6YfbTLTsgrUcr686GdtSQjCfNz5+2o2Mo9IBFVJOrU2fDKn+iZPp8qHrIubHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:18:13.900138Z","bundle_sha256":"c0cd9e0a0791fbba7a713a302c9d1f352626d22b2dca24edb1a402d93f304345"}}