{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ESAUWQAYBSHU325IYOXZTBY47L","short_pith_number":"pith:ESAUWQAY","canonical_record":{"source":{"id":"2406.11303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T08:09:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cbbad0cfa65f07356db53a6454836ddbbcb28753321f70facb3cd336597cdaaf","abstract_canon_sha256":"fbdf2f6465cdded8af0dc9cc3c031ef1e5b814e6863c6bf0b477d4944bd025b7"},"schema_version":"1.0"},"canonical_sha256":"24814b40180c8f4deba8c3af99871cfae2c3c3acd83bdc0d3dc25a97d0646aaa","source":{"kind":"arxiv","id":"2406.11303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11303","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11303v1","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11303","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_12","alias_value":"ESAUWQAYBSHU","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_16","alias_value":"ESAUWQAYBSHU325I","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_8","alias_value":"ESAUWQAY","created_at":"2026-07-05T08:32:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ESAUWQAYBSHU325IYOXZTBY47L","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T08:09:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cbbad0cfa65f07356db53a6454836ddbbcb28753321f70facb3cd336597cdaaf","abstract_canon_sha256":"fbdf2f6465cdded8af0dc9cc3c031ef1e5b814e6863c6bf0b477d4944bd025b7"},"schema_version":"1.0"},"canonical_sha256":"24814b40180c8f4deba8c3af99871cfae2c3c3acd83bdc0d3dc25a97d0646aaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:51.603350Z","signature_b64":"GT7YvOqJJrTy5iBzugN9lt893I7PNJqU2KahvuIR4VkSAXSOD0sJ5LoZBQ/lVVfZ2oyJTGZzjck6cOmVj0UeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24814b40180c8f4deba8c3af99871cfae2c3c3acd83bdc0d3dc25a97d0646aaa","last_reissued_at":"2026-07-05T08:32:51.602855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:51.602855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11303","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":"2026-07-05T08:32:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hkFIV574wawp1Lef+2h7AQApb9+pVbFziJqKozf96UVWwmmjXXHC6ToBOLZKKaZlzq71cHtZ/41uQj8XQTQ+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:29:00.355860Z"},"content_sha256":"d2503d37d5a626538a398ec75122045c75af424546e81202e2eb81ebcd412d4f","schema_version":"1.0","event_id":"sha256:d2503d37d5a626538a398ec75122045c75af424546e81202e2eb81ebcd412d4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ESAUWQAYBSHU325IYOXZTBY47L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baotian Hu, Haoyuan Shi, Longyue Wang, Min Zhang, Xinyu Chen, Yunxin Li","submitted_at":"2024-06-17T08:09:00Z","abstract_excerpt":"Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video understanding and reasoning. To address this, we present VideoVista, a video QA benchmark that integrates challenges across diverse content categories, durations, and abilities. Specifically, VideoVista comprises 25,000 questions derived from 3,400 videos spanning 14 categories (e.g., Howto, Film, and Entertainment) with durations ranging from a few seconds to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11303","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/2406.11303/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":"2026-07-05T08:32:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WocjYM5x4SsV8E/TX7PP3Jh2PL0eVeZeIMOq7FtQ4Ug3ZTGNCDWhi/qu0ItBzAzhJ6uQoE8zGbH8LQfNUuiYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:29:00.356366Z"},"content_sha256":"9a5042a32bf5833d38d9e6bd77402f473a2f61ec6f345d6e956d38a7da926a1c","schema_version":"1.0","event_id":"sha256:9a5042a32bf5833d38d9e6bd77402f473a2f61ec6f345d6e956d38a7da926a1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESAUWQAYBSHU325IYOXZTBY47L/bundle.json","state_url":"https://pith.science/pith/ESAUWQAYBSHU325IYOXZTBY47L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESAUWQAYBSHU325IYOXZTBY47L/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":"2026-08-09T06:29:00Z","links":{"resolver":"https://pith.science/pith/ESAUWQAYBSHU325IYOXZTBY47L","bundle":"https://pith.science/pith/ESAUWQAYBSHU325IYOXZTBY47L/bundle.json","state":"https://pith.science/pith/ESAUWQAYBSHU325IYOXZTBY47L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESAUWQAYBSHU325IYOXZTBY47L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ESAUWQAYBSHU325IYOXZTBY47L","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":"fbdf2f6465cdded8af0dc9cc3c031ef1e5b814e6863c6bf0b477d4944bd025b7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T08:09:00Z","title_canon_sha256":"cbbad0cfa65f07356db53a6454836ddbbcb28753321f70facb3cd336597cdaaf"},"schema_version":"1.0","source":{"id":"2406.11303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11303","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11303v1","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11303","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_12","alias_value":"ESAUWQAYBSHU","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_16","alias_value":"ESAUWQAYBSHU325I","created_at":"2026-07-05T08:32:51Z"},{"alias_kind":"pith_short_8","alias_value":"ESAUWQAY","created_at":"2026-07-05T08:32:51Z"}],"graph_snapshots":[{"event_id":"sha256:9a5042a32bf5833d38d9e6bd77402f473a2f61ec6f345d6e956d38a7da926a1c","target":"graph","created_at":"2026-07-05T08:32:51Z","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/2406.11303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video understanding and reasoning. To address this, we present VideoVista, a video QA benchmark that integrates challenges across diverse content categories, durations, and abilities. Specifically, VideoVista comprises 25,000 questions derived from 3,400 videos spanning 14 categories (e.g., Howto, Film, and Entertainment) with durations ranging from a few seconds to ","authors_text":"Baotian Hu, Haoyuan Shi, Longyue Wang, Min Zhang, Xinyu Chen, Yunxin Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T08:09:00Z","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11303","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:d2503d37d5a626538a398ec75122045c75af424546e81202e2eb81ebcd412d4f","target":"record","created_at":"2026-07-05T08:32:51Z","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":"fbdf2f6465cdded8af0dc9cc3c031ef1e5b814e6863c6bf0b477d4944bd025b7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T08:09:00Z","title_canon_sha256":"cbbad0cfa65f07356db53a6454836ddbbcb28753321f70facb3cd336597cdaaf"},"schema_version":"1.0","source":{"id":"2406.11303","kind":"arxiv","version":1}},"canonical_sha256":"24814b40180c8f4deba8c3af99871cfae2c3c3acd83bdc0d3dc25a97d0646aaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24814b40180c8f4deba8c3af99871cfae2c3c3acd83bdc0d3dc25a97d0646aaa","first_computed_at":"2026-07-05T08:32:51.602855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:51.602855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GT7YvOqJJrTy5iBzugN9lt893I7PNJqU2KahvuIR4VkSAXSOD0sJ5LoZBQ/lVVfZ2oyJTGZzjck6cOmVj0UeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:51.603350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2503d37d5a626538a398ec75122045c75af424546e81202e2eb81ebcd412d4f","sha256:9a5042a32bf5833d38d9e6bd77402f473a2f61ec6f345d6e956d38a7da926a1c"],"state_sha256":"f590acdca5cde6ddaa8e06a60673ba0e440ea15ab3d73f2c57f8c5a77e63de6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTTQ9XnSOKlWmh8IUiKmEzpH6ZdMs23S1dOMDqxPLkaFkd4KmLHg4BvSIZ6xLqlMOcwngunaN3yeTfSLyo0CDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:29:00.360282Z","bundle_sha256":"bb4f8657a610d7649d4f7988eb19a4d12eabde641840561e54a36462c6668ae8"}}