{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6DVJE5ZL5I3CKQWPLM546UIMEQ","short_pith_number":"pith:6DVJE5ZL","canonical_record":{"source":{"id":"2403.10517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"393e25201cb3124d04d170713ce3c22a7fe2ba7776907f2dfe647b9953d41d8e","abstract_canon_sha256":"369f57309dfa178ce7cc279fa922b8699bca5cfcc5f4a0a548c3056f38a8e247"},"schema_version":"1.0"},"canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","source":{"kind":"arxiv","id":"2403.10517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10517","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10517v1","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10517","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_12","alias_value":"6DVJE5ZL5I3C","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_16","alias_value":"6DVJE5ZL5I3CKQWP","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_8","alias_value":"6DVJE5ZL","created_at":"2026-07-05T07:56:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6DVJE5ZL5I3CKQWPLM546UIMEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"393e25201cb3124d04d170713ce3c22a7fe2ba7776907f2dfe647b9953d41d8e","abstract_canon_sha256":"369f57309dfa178ce7cc279fa922b8699bca5cfcc5f4a0a548c3056f38a8e247"},"schema_version":"1.0"},"canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:42.589881Z","signature_b64":"ZXdB5oLR3yR6+KXXBEl3Ol9X7BfyLyquT92ICmEHkgbYpf5ZEYIG4OzHdfbQrFNsdKH5EeBs1qFyHqn/rzXuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","last_reissued_at":"2026-07-05T07:56:42.589366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:42.589366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10517","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":"2026-07-05T07:56:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXuBDuHYK5yeh06UyOl5DcaquK4wgYzJsY10llSfb9mCxfbz0DgDPQqbAjSjql4deAn/8fgLDxamc2apXgzQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:44.960774Z"},"content_sha256":"11c7a160e78f194e1dbdd8c9e017c7a7ede441befdd5593bf7fcc170eb1a5bf0","schema_version":"1.0","event_id":"sha256:11c7a160e78f194e1dbdd8c9e017c7a7ede441befdd5593bf7fcc170eb1a5bf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6DVJE5ZL5I3CKQWPLM546UIMEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Orr Zohar, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2024-03-15T17:57:52Z","abstract_excerpt":"Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10517","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/2403.10517/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":"2026-07-05T07:56:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"boYmzDmu5wWMrqhYDoSQvYfZwFhRBplIT6V5AfEuQ8zlS2BNfNksw5ZKvQ6ZxeYIhMo53ZE6e8qHJ25GmoSDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:44.961330Z"},"content_sha256":"0001ebe19631a0ff124ec49835f6bb79216833cc28c0a48aa8dae8691c9b776a","schema_version":"1.0","event_id":"sha256:0001ebe19631a0ff124ec49835f6bb79216833cc28c0a48aa8dae8691c9b776a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/bundle.json","state_url":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/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":"2026-08-05T01:06:44Z","links":{"resolver":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ","bundle":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/bundle.json","state":"https://pith.science/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DVJE5ZL5I3CKQWPLM546UIMEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6DVJE5ZL5I3CKQWPLM546UIMEQ","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":"369f57309dfa178ce7cc279fa922b8699bca5cfcc5f4a0a548c3056f38a8e247","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","title_canon_sha256":"393e25201cb3124d04d170713ce3c22a7fe2ba7776907f2dfe647b9953d41d8e"},"schema_version":"1.0","source":{"id":"2403.10517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10517","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10517v1","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10517","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_12","alias_value":"6DVJE5ZL5I3C","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_16","alias_value":"6DVJE5ZL5I3CKQWP","created_at":"2026-07-05T07:56:42Z"},{"alias_kind":"pith_short_8","alias_value":"6DVJE5ZL","created_at":"2026-07-05T07:56:42Z"}],"graph_snapshots":[{"event_id":"sha256:0001ebe19631a0ff124ec49835f6bb79216833cc28c0a48aa8dae8691c9b776a","target":"graph","created_at":"2026-07-05T07:56:42Z","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/2403.10517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retri","authors_text":"Orr Zohar, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10517","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":"sha256:11c7a160e78f194e1dbdd8c9e017c7a7ede441befdd5593bf7fcc170eb1a5bf0","target":"record","created_at":"2026-07-05T07:56:42Z","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":"369f57309dfa178ce7cc279fa922b8699bca5cfcc5f4a0a548c3056f38a8e247","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T17:57:52Z","title_canon_sha256":"393e25201cb3124d04d170713ce3c22a7fe2ba7776907f2dfe647b9953d41d8e"},"schema_version":"1.0","source":{"id":"2403.10517","kind":"arxiv","version":1}},"canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0ea92772bea362542cf5b3bcf510c2439a65209fa6169ac0d933c24bdedcff1","first_computed_at":"2026-07-05T07:56:42.589366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:42.589366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZXdB5oLR3yR6+KXXBEl3Ol9X7BfyLyquT92ICmEHkgbYpf5ZEYIG4OzHdfbQrFNsdKH5EeBs1qFyHqn/rzXuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:42.589881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11c7a160e78f194e1dbdd8c9e017c7a7ede441befdd5593bf7fcc170eb1a5bf0","sha256:0001ebe19631a0ff124ec49835f6bb79216833cc28c0a48aa8dae8691c9b776a"],"state_sha256":"73871fae5a6ecfcb40b22de97d4b09dd4fc04a8eb477ee813452152fd1408a44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtJQX8buz2hp/dPflNoIl4BzuIaTn3xjDJc2jm7MduvKe8v15OE+ino0qcbpnrvxq+D8N5YyBGyCE3rK24FmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:06:44.965714Z","bundle_sha256":"ef026abf6c455f85f94db4968ea7649073091f4baf2135fee12525fcbbb9837c"}}