{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D3N6FQDN2QMSBFUWD2EHHAF7U3","short_pith_number":"pith:D3N6FQDN","schema_version":"1.0","canonical_sha256":"1edbe2c06dd4192096961e887380bfa6f810a8f39db6a32ad98938b30f958922","source":{"kind":"arxiv","id":"2308.01907","version":1},"attestation_state":"computed","paper":{"title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Jifeng Dai, Linjie Xing, Min Shi, Qingyun Li, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yu Qiao, Yushi Chen, Zhe Chen, Zhenhang Huang, Zhiguo Cao","submitted_at":"2023-08-03T17:59:47Z","abstract_excerpt":"We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world. Using a scalable data engine that incorporates human feedback and efficient models in the loop, we create a new dataset (AS-1B) with over 1 billion regions annotated with semantic tags, question-answering pairs, and detailed captions. It covers a wide range of 3.5 million common and rare concepts in the real world, and has 132.2 billion tokens that describe the concepts and their attributes. Leveraging this new dataset, we develop the All-Seeing model (ASM), a un"},"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":"2308.01907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-03T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"856bc65443e59cd8f2f7b853b97e3e4696055039896f9051757812761fcbb6a7","abstract_canon_sha256":"a40b32b86ba394b9b2606e5eba59233a12c6d43a27c19489671629b83555dea1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:25.111393Z","signature_b64":"fg4VCHKbfaMR4+JZqXgXoYtY2tTI1gyrWfbm5NpQ7+bMnrG0zIkqvcIJOvpDuCXJYDakxhoCtONhvrKCUjcsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1edbe2c06dd4192096961e887380bfa6f810a8f39db6a32ad98938b30f958922","last_reissued_at":"2026-07-05T06:37:25.110887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:25.110887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Jifeng Dai, Linjie Xing, Min Shi, Qingyun Li, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yu Qiao, Yushi Chen, Zhe Chen, Zhenhang Huang, Zhiguo Cao","submitted_at":"2023-08-03T17:59:47Z","abstract_excerpt":"We present the All-Seeing (AS) project: a large-scale data and model for recognizing and understanding everything in the open world. Using a scalable data engine that incorporates human feedback and efficient models in the loop, we create a new dataset (AS-1B) with over 1 billion regions annotated with semantic tags, question-answering pairs, and detailed captions. It covers a wide range of 3.5 million common and rare concepts in the real world, and has 132.2 billion tokens that describe the concepts and their attributes. Leveraging this new dataset, we develop the All-Seeing model (ASM), a un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01907","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/2308.01907/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":"2308.01907","created_at":"2026-07-05T06:37:25.110952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01907v1","created_at":"2026-07-05T06:37:25.110952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01907","created_at":"2026-07-05T06:37:25.110952+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3N6FQDN2QMS","created_at":"2026-07-05T06:37:25.110952+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3N6FQDN2QMSBFUW","created_at":"2026-07-05T06:37:25.110952+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3N6FQDN","created_at":"2026-07-05T06:37:25.110952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00592","citing_title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21977","citing_title":"Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07825","citing_title":"Anisotropic Modality Align","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3","json":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3.json","graph_json":"https://pith.science/api/pith-number/D3N6FQDN2QMSBFUWD2EHHAF7U3/graph.json","events_json":"https://pith.science/api/pith-number/D3N6FQDN2QMSBFUWD2EHHAF7U3/events.json","paper":"https://pith.science/paper/D3N6FQDN"},"agent_actions":{"view_html":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3","download_json":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3.json","view_paper":"https://pith.science/paper/D3N6FQDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01907&json=true","fetch_graph":"https://pith.science/api/pith-number/D3N6FQDN2QMSBFUWD2EHHAF7U3/graph.json","fetch_events":"https://pith.science/api/pith-number/D3N6FQDN2QMSBFUWD2EHHAF7U3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3/action/storage_attestation","attest_author":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3/action/author_attestation","sign_citation":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3/action/citation_signature","submit_replication":"https://pith.science/pith/D3N6FQDN2QMSBFUWD2EHHAF7U3/action/replication_record"}},"created_at":"2026-07-05T06:37:25.110952+00:00","updated_at":"2026-07-05T06:37:25.110952+00:00"}