{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ERBIP4X4FLVBOAU26WWTIOM6NS","short_pith_number":"pith:ERBIP4X4","schema_version":"1.0","canonical_sha256":"244287f2fc2aea17029af5ad34399e6ca71a5f8df24f4e70b2a438cb0d824f83","source":{"kind":"arxiv","id":"2402.04841","version":1},"attestation_state":"computed","paper":{"title":"Data-efficient Large Vision Models through Sequential Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chengcheng Wang, Han Hu, Han Wu, Jianyuan Guo, Kai Han, Yehui Tang, Zhiwei Hao","submitted_at":"2024-02-07T13:41:53Z","abstract_excerpt":"Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to out-of-domain tasks. However, current endeavors are hamstrung by an over-reliance on colossal models, exemplified by models with upwards of 3B parameters, and the necessity for an extensive corpus of visual data, often comprising a staggering 400B tokens. In this paper, we delve into the development of an efficient, autoregression-based vision model, innovatively"},"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":"2402.04841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T13:41:53Z","cross_cats_sorted":[],"title_canon_sha256":"60ad2b3528e14af5822a62a4cae9127c3be70c7e035bdda1beab38f1ed4a9269","abstract_canon_sha256":"b57fa59add5d4f206f049357a320d66d1181f5da0dbcbbf12112b3721ef924f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:05.657386Z","signature_b64":"ScgRVgsizbCu1sjTjH0qFQ6uiwdQmF/BlL0DMlQqU03i44bx6XL2YasPUEIdiALEeIeN7NiGFgrfFEE6bw3ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244287f2fc2aea17029af5ad34399e6ca71a5f8df24f4e70b2a438cb0d824f83","last_reissued_at":"2026-07-05T08:28:05.656861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:05.656861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-efficient Large Vision Models through Sequential Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chengcheng Wang, Han Hu, Han Wu, Jianyuan Guo, Kai Han, Yehui Tang, Zhiwei Hao","submitted_at":"2024-02-07T13:41:53Z","abstract_excerpt":"Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to out-of-domain tasks. However, current endeavors are hamstrung by an over-reliance on colossal models, exemplified by models with upwards of 3B parameters, and the necessity for an extensive corpus of visual data, often comprising a staggering 400B tokens. In this paper, we delve into the development of an efficient, autoregression-based vision model, innovatively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04841","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/2402.04841/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":"2402.04841","created_at":"2026-07-05T08:28:05.656925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04841v1","created_at":"2026-07-05T08:28:05.656925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04841","created_at":"2026-07-05T08:28:05.656925+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERBIP4X4FLVB","created_at":"2026-07-05T08:28:05.656925+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERBIP4X4FLVBOAU2","created_at":"2026-07-05T08:28:05.656925+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERBIP4X4","created_at":"2026-07-05T08:28:05.656925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10905","citing_title":"Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06748","citing_title":"From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05651","citing_title":"Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS","json":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS.json","graph_json":"https://pith.science/api/pith-number/ERBIP4X4FLVBOAU26WWTIOM6NS/graph.json","events_json":"https://pith.science/api/pith-number/ERBIP4X4FLVBOAU26WWTIOM6NS/events.json","paper":"https://pith.science/paper/ERBIP4X4"},"agent_actions":{"view_html":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS","download_json":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS.json","view_paper":"https://pith.science/paper/ERBIP4X4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04841&json=true","fetch_graph":"https://pith.science/api/pith-number/ERBIP4X4FLVBOAU26WWTIOM6NS/graph.json","fetch_events":"https://pith.science/api/pith-number/ERBIP4X4FLVBOAU26WWTIOM6NS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS/action/storage_attestation","attest_author":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS/action/author_attestation","sign_citation":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS/action/citation_signature","submit_replication":"https://pith.science/pith/ERBIP4X4FLVBOAU26WWTIOM6NS/action/replication_record"}},"created_at":"2026-07-05T08:28:05.656925+00:00","updated_at":"2026-07-05T08:28:05.656925+00:00"}