{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGRRPB6LHD36LFY4CP7ZPKWYJ4","short_pith_number":"pith:FGRRPB6L","canonical_record":{"source":{"id":"2509.07680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T17:59:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63f687df0ec5d3b7ff4e9d34d266a1ab669e8396b7d98b896842da84ac8c1a20","abstract_canon_sha256":"d86a70a224eb9bfc90345fe2f42ba8ca4e9abd3b53fe0d7a0711e7ea93541ef3"},"schema_version":"1.0"},"canonical_sha256":"29a31787cb38f7e5971c13ff97aad84f11b26a3354a24fa12b0779068cf00e5f","source":{"kind":"arxiv","id":"2509.07680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07680","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07680v1","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07680","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"FGRRPB6LHD36","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"FGRRPB6LHD36LFY4","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"FGRRPB6L","created_at":"2026-07-05T12:07:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGRRPB6LHD36LFY4CP7ZPKWYJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2509.07680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T17:59:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63f687df0ec5d3b7ff4e9d34d266a1ab669e8396b7d98b896842da84ac8c1a20","abstract_canon_sha256":"d86a70a224eb9bfc90345fe2f42ba8ca4e9abd3b53fe0d7a0711e7ea93541ef3"},"schema_version":"1.0"},"canonical_sha256":"29a31787cb38f7e5971c13ff97aad84f11b26a3354a24fa12b0779068cf00e5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:26.298374Z","signature_b64":"dTYBPZP+9VzrCqwtRnQd4aQwuUldnSZzWYhMWZj+EgSPkSN+7ORwIMC8v/cLDaQ4UiuUs/au8vkuXGIyjIDcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a31787cb38f7e5971c13ff97aad84f11b26a3354a24fa12b0779068cf00e5f","last_reissued_at":"2026-07-05T12:07:26.297868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:26.297868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.07680","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uff668sM2pPzBssNoYBYAtwGpDy23J4NcUDTBBhlQKge3Sce+3/NI4YHSMxa+6xoa8URA+CUbir+lC98G8tsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:26:13.917716Z"},"content_sha256":"432614cfa35e9d85f8379c2e2db8e755c4ed61c84e634b33accf80f612bc539a","schema_version":"1.0","event_id":"sha256:432614cfa35e9d85f8379c2e2db8e755c4ed61c84e634b33accf80f612bc539a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGRRPB6LHD36LFY4CP7ZPKWYJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAViAR: Critic-Augmented Video Agentic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Arsha Nagrani, Carl Vondrick, Cordelia Schmid, Sachit Menon, Tobias Weyand","submitted_at":"2025-09-09T17:59:39Z","abstract_excerpt":"Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance wanes for tasks requiring complex reasoning on videos as queries grow more complex and videos grow longer. In this work, we ask: can existing perception capabilities be leveraged to successfully perform more complex video reasoning? In particular, we develop a large language model agent given access to video modules as subagents or tools. Rather than followi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07680","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.07680/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EArYBEOxlEjFYvLAFDLHViHxnxNDpiw62sVDhzYtKgG7OQtiIkJnvAZGkO6zyNo0ftP0lz9LiIx5U7vTbgQLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:26:13.918626Z"},"content_sha256":"ad063d7f506552db138b0645be24a819efaf293993459d1063c5f28e0537eba4","schema_version":"1.0","event_id":"sha256:ad063d7f506552db138b0645be24a819efaf293993459d1063c5f28e0537eba4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/bundle.json","state_url":"https://pith.science/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/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":"2026-08-05T13:26:13Z","links":{"resolver":"https://pith.science/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4","bundle":"https://pith.science/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/bundle.json","state":"https://pith.science/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGRRPB6LHD36LFY4CP7ZPKWYJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGRRPB6LHD36LFY4CP7ZPKWYJ4","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":"d86a70a224eb9bfc90345fe2f42ba8ca4e9abd3b53fe0d7a0711e7ea93541ef3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T17:59:39Z","title_canon_sha256":"63f687df0ec5d3b7ff4e9d34d266a1ab669e8396b7d98b896842da84ac8c1a20"},"schema_version":"1.0","source":{"id":"2509.07680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.07680","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.07680v1","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07680","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"FGRRPB6LHD36","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"FGRRPB6LHD36LFY4","created_at":"2026-07-05T12:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"FGRRPB6L","created_at":"2026-07-05T12:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:ad063d7f506552db138b0645be24a819efaf293993459d1063c5f28e0537eba4","target":"graph","created_at":"2026-07-05T12:07:26Z","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/2509.07680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance wanes for tasks requiring complex reasoning on videos as queries grow more complex and videos grow longer. In this work, we ask: can existing perception capabilities be leveraged to successfully perform more complex video reasoning? In particular, we develop a large language model agent given access to video modules as subagents or tools. Rather than followi","authors_text":"Ahmet Iscen, Arsha Nagrani, Carl Vondrick, Cordelia Schmid, Sachit Menon, Tobias Weyand","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T17:59:39Z","title":"CAViAR: Critic-Augmented Video Agentic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07680","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":"sha256:432614cfa35e9d85f8379c2e2db8e755c4ed61c84e634b33accf80f612bc539a","target":"record","created_at":"2026-07-05T12:07:26Z","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":"d86a70a224eb9bfc90345fe2f42ba8ca4e9abd3b53fe0d7a0711e7ea93541ef3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-09T17:59:39Z","title_canon_sha256":"63f687df0ec5d3b7ff4e9d34d266a1ab669e8396b7d98b896842da84ac8c1a20"},"schema_version":"1.0","source":{"id":"2509.07680","kind":"arxiv","version":1}},"canonical_sha256":"29a31787cb38f7e5971c13ff97aad84f11b26a3354a24fa12b0779068cf00e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29a31787cb38f7e5971c13ff97aad84f11b26a3354a24fa12b0779068cf00e5f","first_computed_at":"2026-07-05T12:07:26.297868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:26.297868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTYBPZP+9VzrCqwtRnQd4aQwuUldnSZzWYhMWZj+EgSPkSN+7ORwIMC8v/cLDaQ4UiuUs/au8vkuXGIyjIDcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:26.298374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.07680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432614cfa35e9d85f8379c2e2db8e755c4ed61c84e634b33accf80f612bc539a","sha256:ad063d7f506552db138b0645be24a819efaf293993459d1063c5f28e0537eba4"],"state_sha256":"9ab278aad36836c0c2bbb296060a18411283c0f168553fb525ac1048bcc1701b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNf8GeRlxYCbmhvL3eu+4oX2AVZhThu5jDM3GnpTZjmxsar7KQQojjzemB2aDj8qgZXXEiMaxHgfoJBeylN/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:26:13.924915Z","bundle_sha256":"f535360a03af49e6f8adf61843c55b61a41c2afaf45d2b1047b9f995221cfe6e"}}