{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BOZL5Q423FWXIQLVJRSNMLPFX2","short_pith_number":"pith:BOZL5Q42","schema_version":"1.0","canonical_sha256":"0bb2bec39ad96d7441754c64d62de5be8d2630518b3c84caa143927e24c4c0dd","source":{"kind":"arxiv","id":"1705.07208","version":2},"attestation_state":"computed","paper":{"title":"PixColor: Pixel Recursive Colorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Bieber, Jonathon Shlens, Kevin Murphy, Mohammad Norouzi, Ryan Dahl, Sergio Guadarrama","submitted_at":"2017-05-19T22:10:51Z","abstract_excerpt":"We propose a novel approach to automatically produce multiple colorized versions of a grayscale image. Our method results from the observation that the task of automated colorization is relatively easy given a low-resolution version of the color image. We first train a conditional PixelCNN to generate a low resolution color for a given grayscale image. Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image. We demonstrate that our approach produces more diverse and plausible c"},"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":"1705.07208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-19T22:10:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f7004a4fd915876da2814a4d8786f6f8a534a54237c9b63c54e00b901f50b24","abstract_canon_sha256":"77300cf788eec6f6554d6cf3c2f131348823aef96f055d94ec95fde9b7c9cf79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:57.244742Z","signature_b64":"b9ZibAg9Kt9HFwRNATVscE1ihqplazIR3Hwi5JH3FWAOzkSlSgoNB5slIZv74nHyP3V29UbEiJsbMxnRU7DNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bb2bec39ad96d7441754c64d62de5be8d2630518b3c84caa143927e24c4c0dd","last_reissued_at":"2026-05-18T00:42:57.244005Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:57.244005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixColor: Pixel Recursive Colorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Bieber, Jonathon Shlens, Kevin Murphy, Mohammad Norouzi, Ryan Dahl, Sergio Guadarrama","submitted_at":"2017-05-19T22:10:51Z","abstract_excerpt":"We propose a novel approach to automatically produce multiple colorized versions of a grayscale image. Our method results from the observation that the task of automated colorization is relatively easy given a low-resolution version of the color image. We first train a conditional PixelCNN to generate a low resolution color for a given grayscale image. Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image. We demonstrate that our approach produces more diverse and plausible c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07208","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1705.07208","created_at":"2026-05-18T00:42:57.244120+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07208v2","created_at":"2026-05-18T00:42:57.244120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07208","created_at":"2026-05-18T00:42:57.244120+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOZL5Q423FWX","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOZL5Q423FWXIQLV","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOZL5Q42","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09909","citing_title":"Deep Exemplar-based Video Colorization","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02392","citing_title":"Guided Image Generation with Conditional Invertible Neural Networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2","json":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2.json","graph_json":"https://pith.science/api/pith-number/BOZL5Q423FWXIQLVJRSNMLPFX2/graph.json","events_json":"https://pith.science/api/pith-number/BOZL5Q423FWXIQLVJRSNMLPFX2/events.json","paper":"https://pith.science/paper/BOZL5Q42"},"agent_actions":{"view_html":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2","download_json":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2.json","view_paper":"https://pith.science/paper/BOZL5Q42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07208&json=true","fetch_graph":"https://pith.science/api/pith-number/BOZL5Q423FWXIQLVJRSNMLPFX2/graph.json","fetch_events":"https://pith.science/api/pith-number/BOZL5Q423FWXIQLVJRSNMLPFX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2/action/storage_attestation","attest_author":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2/action/author_attestation","sign_citation":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2/action/citation_signature","submit_replication":"https://pith.science/pith/BOZL5Q423FWXIQLVJRSNMLPFX2/action/replication_record"}},"created_at":"2026-05-18T00:42:57.244120+00:00","updated_at":"2026-05-18T00:42:57.244120+00:00"}