{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XXFWB3KD4QPIJ7JWAQH254YHYB","short_pith_number":"pith:XXFWB3KD","schema_version":"1.0","canonical_sha256":"bdcb60ed43e41e84fd36040faef307c050aceea4a1bfe66caf050d2a3697054e","source":{"kind":"arxiv","id":"2311.16103","version":2},"attestation_state":"computed","paper":{"title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Lin, Bin Zhu, Dongdong Chen, Jiaxi Cui, Li Yuan, Lu Yuan, Munan Ning, Yujia Xie","submitted_at":"2023-11-27T18:59:58Z","abstract_excerpt":"Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving artificial general intelligence, a truly intelligent Video-LLM model should not only see and understand the surroundings, but also possess human-level commonsense, and make well-informed decisions for the users. To guide the development of such a model, the establishment of a robust and comprehensive evaluation system becomes crucial. To this end, this paper prop"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.16103","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T18:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"931ae823bf7ab32b39d4fe97327d489a7b18cc3de86af8beeeeaee4c35700b95","abstract_canon_sha256":"50a2717a11cc1a407536ff32056aa7a64a790e5f137e4303c76592f43d12f6d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:35.733539Z","signature_b64":"Rvt32mOrlQY9UeeeaeS3GwS6X3vjvGIN29/43/u2NOGPkMFj9wwJ2KEm0OeqtjgsxUhF0wlMbivlhcfCVFfWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdcb60ed43e41e84fd36040faef307c050aceea4a1bfe66caf050d2a3697054e","last_reissued_at":"2026-07-05T07:17:35.733055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:35.733055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Lin, Bin Zhu, Dongdong Chen, Jiaxi Cui, Li Yuan, Lu Yuan, Munan Ning, Yujia Xie","submitted_at":"2023-11-27T18:59:58Z","abstract_excerpt":"Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving artificial general intelligence, a truly intelligent Video-LLM model should not only see and understand the surroundings, but also possess human-level commonsense, and make well-informed decisions for the users. To guide the development of such a model, the establishment of a robust and comprehensive evaluation system becomes crucial. To this end, this paper prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16103","kind":"arxiv","version":2},"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/2311.16103/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.16103","created_at":"2026-07-05T07:17:35.733108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16103v2","created_at":"2026-07-05T07:17:35.733108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16103","created_at":"2026-07-05T07:17:35.733108+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXFWB3KD4QPI","created_at":"2026-07-05T07:17:35.733108+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXFWB3KD4QPIJ7JW","created_at":"2026-07-05T07:17:35.733108+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXFWB3KD","created_at":"2026-07-05T07:17:35.733108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05425","citing_title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04326","citing_title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2403.00476","citing_title":"TempCompass: Do Video LLMs Really Understand Videos?","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13281","citing_title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15724","citing_title":"VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04264","citing_title":"MLVU: Benchmarking Multi-task Long Video Understanding","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22884","citing_title":"Can Multimodal Large Language Models Truly Understand Small Objects?","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":183,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB","json":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB.json","graph_json":"https://pith.science/api/pith-number/XXFWB3KD4QPIJ7JWAQH254YHYB/graph.json","events_json":"https://pith.science/api/pith-number/XXFWB3KD4QPIJ7JWAQH254YHYB/events.json","paper":"https://pith.science/paper/XXFWB3KD"},"agent_actions":{"view_html":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB","download_json":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB.json","view_paper":"https://pith.science/paper/XXFWB3KD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16103&json=true","fetch_graph":"https://pith.science/api/pith-number/XXFWB3KD4QPIJ7JWAQH254YHYB/graph.json","fetch_events":"https://pith.science/api/pith-number/XXFWB3KD4QPIJ7JWAQH254YHYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB/action/storage_attestation","attest_author":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB/action/author_attestation","sign_citation":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB/action/citation_signature","submit_replication":"https://pith.science/pith/XXFWB3KD4QPIJ7JWAQH254YHYB/action/replication_record"}},"created_at":"2026-07-05T07:17:35.733108+00:00","updated_at":"2026-07-05T07:17:35.733108+00:00"}