{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HLIAJPP32CKOXJACYLKZNTL2NV","short_pith_number":"pith:HLIAJPP3","schema_version":"1.0","canonical_sha256":"3ad004bdfbd094eba402c2d596cd7a6d54d3d408bec687a668bc26cc39a066eb","source":{"kind":"arxiv","id":"2605.30341","version":1},"attestation_state":"computed","paper":{"title":"GPIC: A Giant Permissive Image Corpus for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Juan Carlos Niebles, Justin Johnson, Keshigeyan Chandrasegaran, Kyle Sargent, Li Fei-Fei, Michael Jang, Michael Poli, Suchir Agarwal","submitted_at":"2026-05-28T17:59:26Z","abstract_excerpt":"Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language model, including 100M training, 200K validation, and 1M test examples. Moreover, all GPIC images are permissively licensed for both research and commercial use. GPIC is safety-filtered, deduplicated, and centrally hosted on Hugging Face. We provide a benchmarking protocol for generative modeling on GPIC. Finally, we p"},"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":"2605.30341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:59:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8109f0f2b35d3a8c1d7fbf381b5080c5e3f53f57697facb943da5bdff5de988a","abstract_canon_sha256":"b7da2b6a273a0a2adc5d485888bc76f82626453755bdef2298be85da2b70c1bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:17.040402Z","signature_b64":"JjsUACnx8rRtmQioNNcS3TdOM5v4sml6LmJOzWLyZ+YXjKKLmb79EjumZetHW6uWY41a/Qke2oP5OeyDr5SVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ad004bdfbd094eba402c2d596cd7a6d54d3d408bec687a668bc26cc39a066eb","last_reissued_at":"2026-05-29T02:06:17.039979Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:17.039979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPIC: A Giant Permissive Image Corpus for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Juan Carlos Niebles, Justin Johnson, Keshigeyan Chandrasegaran, Kyle Sargent, Li Fei-Fei, Michael Jang, Michael Poli, Suchir Agarwal","submitted_at":"2026-05-28T17:59:26Z","abstract_excerpt":"Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language model, including 100M training, 200K validation, and 1M test examples. Moreover, all GPIC images are permissively licensed for both research and commercial use. GPIC is safety-filtered, deduplicated, and centrally hosted on Hugging Face. We provide a benchmarking protocol for generative modeling on GPIC. Finally, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30341","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/2605.30341/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":"2605.30341","created_at":"2026-05-29T02:06:17.040042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30341v1","created_at":"2026-05-29T02:06:17.040042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30341","created_at":"2026-05-29T02:06:17.040042+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLIAJPP32CKO","created_at":"2026-05-29T02:06:17.040042+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLIAJPP32CKOXJAC","created_at":"2026-05-29T02:06:17.040042+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLIAJPP3","created_at":"2026-05-29T02:06:17.040042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV","json":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV.json","graph_json":"https://pith.science/api/pith-number/HLIAJPP32CKOXJACYLKZNTL2NV/graph.json","events_json":"https://pith.science/api/pith-number/HLIAJPP32CKOXJACYLKZNTL2NV/events.json","paper":"https://pith.science/paper/HLIAJPP3"},"agent_actions":{"view_html":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV","download_json":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV.json","view_paper":"https://pith.science/paper/HLIAJPP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30341&json=true","fetch_graph":"https://pith.science/api/pith-number/HLIAJPP32CKOXJACYLKZNTL2NV/graph.json","fetch_events":"https://pith.science/api/pith-number/HLIAJPP32CKOXJACYLKZNTL2NV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV/action/storage_attestation","attest_author":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV/action/author_attestation","sign_citation":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV/action/citation_signature","submit_replication":"https://pith.science/pith/HLIAJPP32CKOXJACYLKZNTL2NV/action/replication_record"}},"created_at":"2026-05-29T02:06:17.040042+00:00","updated_at":"2026-05-29T02:06:17.040042+00:00"}