{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QN3I2RBAHGDE26RUX7FZRX2M3M","short_pith_number":"pith:QN3I2RBA","schema_version":"1.0","canonical_sha256":"83768d442039864d7a34bfcb98df4cdb0603af3d275d62b3203a5fcf05c7ba82","source":{"kind":"arxiv","id":"2310.16825","version":1},"attestation_state":"computed","paper":{"title":"CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Aaron Gokaslan, A. Feder Cooper, Austin Jacobson, Cory Stephenson, Jasmine Collins, Jonathan Frankle, Landan Seguin, Mihir Patel, Volodymyr Kuleshov","submitted_at":"2023-10-25T17:56:07Z","abstract_excerpt":"We assemble a dataset of Creative-Commons-licensed (CC) images, which we use to train a set of open diffusion models that are qualitatively competitive with Stable Diffusion 2 (SD2). This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce. In turn, to address these challenges, we use an intuitive transfer learning technique to produce a set of high-quality synthetic captions paired with curated CC images. We then develop a data- and compute-efficient training recipe that requires "},"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":"2310.16825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T17:56:07Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"89bffd4c7c11e6dc26f006c7425682c9eac1e890d8f6610a311299b5505f6724","abstract_canon_sha256":"154c26dbefe029c49201204479f6bd102c0e31df06cf866ffaede90ce38a00b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:03.290619Z","signature_b64":"ZJhBuuMgS047tV5EQ3Cyy58tqab7iNzOcAearPCFQBVW2wFufQx/LZgmrF+lMHIflzols3A8uOmhs2dH7SLFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83768d442039864d7a34bfcb98df4cdb0603af3d275d62b3203a5fcf05c7ba82","last_reissued_at":"2026-07-05T07:05:03.290072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:03.290072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Aaron Gokaslan, A. Feder Cooper, Austin Jacobson, Cory Stephenson, Jasmine Collins, Jonathan Frankle, Landan Seguin, Mihir Patel, Volodymyr Kuleshov","submitted_at":"2023-10-25T17:56:07Z","abstract_excerpt":"We assemble a dataset of Creative-Commons-licensed (CC) images, which we use to train a set of open diffusion models that are qualitatively competitive with Stable Diffusion 2 (SD2). This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce. In turn, to address these challenges, we use an intuitive transfer learning technique to produce a set of high-quality synthetic captions paired with curated CC images. We then develop a data- and compute-efficient training recipe that requires "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16825","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/2310.16825/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":"2310.16825","created_at":"2026-07-05T07:05:03.290133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16825v1","created_at":"2026-07-05T07:05:03.290133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16825","created_at":"2026-07-05T07:05:03.290133+00:00"},{"alias_kind":"pith_short_12","alias_value":"QN3I2RBAHGDE","created_at":"2026-07-05T07:05:03.290133+00:00"},{"alias_kind":"pith_short_16","alias_value":"QN3I2RBAHGDE26RU","created_at":"2026-07-05T07:05:03.290133+00:00"},{"alias_kind":"pith_short_8","alias_value":"QN3I2RBA","created_at":"2026-07-05T07:05:03.290133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21272","citing_title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M","json":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M.json","graph_json":"https://pith.science/api/pith-number/QN3I2RBAHGDE26RUX7FZRX2M3M/graph.json","events_json":"https://pith.science/api/pith-number/QN3I2RBAHGDE26RUX7FZRX2M3M/events.json","paper":"https://pith.science/paper/QN3I2RBA"},"agent_actions":{"view_html":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M","download_json":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M.json","view_paper":"https://pith.science/paper/QN3I2RBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16825&json=true","fetch_graph":"https://pith.science/api/pith-number/QN3I2RBAHGDE26RUX7FZRX2M3M/graph.json","fetch_events":"https://pith.science/api/pith-number/QN3I2RBAHGDE26RUX7FZRX2M3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M/action/storage_attestation","attest_author":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M/action/author_attestation","sign_citation":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M/action/citation_signature","submit_replication":"https://pith.science/pith/QN3I2RBAHGDE26RUX7FZRX2M3M/action/replication_record"}},"created_at":"2026-07-05T07:05:03.290133+00:00","updated_at":"2026-07-05T07:05:03.290133+00:00"}