{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V5F2GF3F42QPINKHN4JSZIJSB7","short_pith_number":"pith:V5F2GF3F","schema_version":"1.0","canonical_sha256":"af4ba31765e6a0f435476f132ca1320fdc90806ffa08972f3ea1f6e83c84022a","source":{"kind":"arxiv","id":"2410.03051","version":4},"attestation_state":"computed","paper":{"title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlin Meng, Christopher D. Manning, Enxin Song, Jenq-Neng Hwang, Omer Bar-Tal, Saining Xie, Vashisht Madhavan, Wenhao Chai, Yilun Du","submitted_at":"2024-10-04T00:13:54Z","abstract_excerpt":"Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap s"},"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":"2410.03051","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:13:54Z","cross_cats_sorted":[],"title_canon_sha256":"fee90ff37463c684d88619a94167f1b09c4c29918471cd94ac5543222b5ee8b6","abstract_canon_sha256":"4f83489b3483b5a0a5a7cda2a299da278743ec4233bdf65c3c0b0a82171a7e1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:20.756968Z","signature_b64":"FyDan8IMay0Agqdo8i8iOTZAFtxN2cX6Qkhd1lGjcgZsgr16AWxbs3ZV6qvx57eHe8NhHXziFVtP1RDTJ6U9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af4ba31765e6a0f435476f132ca1320fdc90806ffa08972f3ea1f6e83c84022a","last_reissued_at":"2026-07-05T10:46:20.756498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:20.756498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlin Meng, Christopher D. Manning, Enxin Song, Jenq-Neng Hwang, Omer Bar-Tal, Saining Xie, Vashisht Madhavan, Wenhao Chai, Yilun Du","submitted_at":"2024-10-04T00:13:54Z","abstract_excerpt":"Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03051","kind":"arxiv","version":4},"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/2410.03051/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":"2410.03051","created_at":"2026-07-05T10:46:20.756555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03051v4","created_at":"2026-07-05T10:46:20.756555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03051","created_at":"2026-07-05T10:46:20.756555+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5F2GF3F42QP","created_at":"2026-07-05T10:46:20.756555+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5F2GF3F42QPINKH","created_at":"2026-07-05T10:46:20.756555+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5F2GF3F","created_at":"2026-07-05T10:46:20.756555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21949","citing_title":"CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05552","citing_title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06532","citing_title":"GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01900","citing_title":"Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2412.17574","citing_title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14075","citing_title":"Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01400","citing_title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22911","citing_title":"ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06080","citing_title":"MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21718","citing_title":"Building a Precise Video Language with Human-AI Oversight","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7","json":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7.json","graph_json":"https://pith.science/api/pith-number/V5F2GF3F42QPINKHN4JSZIJSB7/graph.json","events_json":"https://pith.science/api/pith-number/V5F2GF3F42QPINKHN4JSZIJSB7/events.json","paper":"https://pith.science/paper/V5F2GF3F"},"agent_actions":{"view_html":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7","download_json":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7.json","view_paper":"https://pith.science/paper/V5F2GF3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03051&json=true","fetch_graph":"https://pith.science/api/pith-number/V5F2GF3F42QPINKHN4JSZIJSB7/graph.json","fetch_events":"https://pith.science/api/pith-number/V5F2GF3F42QPINKHN4JSZIJSB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7/action/storage_attestation","attest_author":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7/action/author_attestation","sign_citation":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7/action/citation_signature","submit_replication":"https://pith.science/pith/V5F2GF3F42QPINKHN4JSZIJSB7/action/replication_record"}},"created_at":"2026-07-05T10:46:20.756555+00:00","updated_at":"2026-07-05T10:46:20.756555+00:00"}