{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KF5QBVNCXRKXLDSZVM4CVRHDED","short_pith_number":"pith:KF5QBVNC","schema_version":"1.0","canonical_sha256":"517b00d5a2bc55758e59ab382ac4e320e0aa87713b420a2c8727a0d31c83aa99","source":{"kind":"arxiv","id":"2209.09019","version":1},"attestation_state":"computed","paper":{"title":"LAVIS: A Library for Language-Vision Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongxu Li, Guangsen Wang, Hung Le, Junnan Li, Silvio Savarese, Steven C.H. Hoi","submitted_at":"2022-09-15T18:04:10Z","abstract_excerpt":"We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent advancements in the language-vision field accessible for researchers and practitioners, as well as fertilizing future research and development. It features a unified interface to easily access state-of-the-art image-language, video-language models and common datasets. LAVIS supports training, evaluation and benchmarking on a rich variety of tasks, including multimodal classification, retrieval, captioning, visual ques"},"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":"2209.09019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-15T18:04:10Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4295824f7ced78fb595ef247f3998ff15e6c84ae394304e38bd2194a183cfb56","abstract_canon_sha256":"e11c27a932b45b4cb89acd3dbeadab7037ed4bfeb42660809bb9990ed0a41092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:48.635596Z","signature_b64":"M4e9ckuXwnn7jN7Hkw5XqlYmCVG/Qp31fN6v7Qjh3XJwKWwlRhEOrJYbtEheQHFn2+9qyfMR7MoI06P6cDRCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517b00d5a2bc55758e59ab382ac4e320e0aa87713b420a2c8727a0d31c83aa99","last_reissued_at":"2026-07-05T04:58:48.635075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:48.635075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAVIS: A Library for Language-Vision Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongxu Li, Guangsen Wang, Hung Le, Junnan Li, Silvio Savarese, Steven C.H. Hoi","submitted_at":"2022-09-15T18:04:10Z","abstract_excerpt":"We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent advancements in the language-vision field accessible for researchers and practitioners, as well as fertilizing future research and development. It features a unified interface to easily access state-of-the-art image-language, video-language models and common datasets. LAVIS supports training, evaluation and benchmarking on a rich variety of tasks, including multimodal classification, retrieval, captioning, visual ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09019","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/2209.09019/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":"2209.09019","created_at":"2026-07-05T04:58:48.635139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09019v1","created_at":"2026-07-05T04:58:48.635139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09019","created_at":"2026-07-05T04:58:48.635139+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF5QBVNCXRKX","created_at":"2026-07-05T04:58:48.635139+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF5QBVNCXRKXLDSZ","created_at":"2026-07-05T04:58:48.635139+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF5QBVNC","created_at":"2026-07-05T04:58:48.635139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00991","citing_title":"Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13050","citing_title":"Modality-Inconsistent Continual Learning of Multimodal Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10355","citing_title":"Evaluating Object Hallucination in Large Vision-Language Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED","json":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED.json","graph_json":"https://pith.science/api/pith-number/KF5QBVNCXRKXLDSZVM4CVRHDED/graph.json","events_json":"https://pith.science/api/pith-number/KF5QBVNCXRKXLDSZVM4CVRHDED/events.json","paper":"https://pith.science/paper/KF5QBVNC"},"agent_actions":{"view_html":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED","download_json":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED.json","view_paper":"https://pith.science/paper/KF5QBVNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09019&json=true","fetch_graph":"https://pith.science/api/pith-number/KF5QBVNCXRKXLDSZVM4CVRHDED/graph.json","fetch_events":"https://pith.science/api/pith-number/KF5QBVNCXRKXLDSZVM4CVRHDED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED/action/storage_attestation","attest_author":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED/action/author_attestation","sign_citation":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED/action/citation_signature","submit_replication":"https://pith.science/pith/KF5QBVNCXRKXLDSZVM4CVRHDED/action/replication_record"}},"created_at":"2026-07-05T04:58:48.635139+00:00","updated_at":"2026-07-05T04:58:48.635139+00:00"}