{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RRI3GKF3TL23Q4SXZJCKHHRCBK","short_pith_number":"pith:RRI3GKF3","schema_version":"1.0","canonical_sha256":"8c51b328bb9af5b87257ca44a39e220a9d0317ced75b599f455c62865cfd891e","source":{"kind":"arxiv","id":"2012.04567","version":5},"attestation_state":"computed","paper":{"title":"Bayesian Image Reconstruction using Deep Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Daniel Moyer, Polina Golland, Razvan V Marinescu","submitted_at":"2020-12-08T17:11:26Z","abstract_excerpt":"Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images. However, these end-to-end approaches require re-training every time there is a distribution shift in the inputs (e.g., night images vs daylight) or relevant latent variables (e.g., camera blur or hand motion). In this work, we leverage state-of-the-art (SOTA) generative models (here StyleGAN2) for building powerful image priors, which enable application of Bayes' "},"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":"2012.04567","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T17:11:26Z","cross_cats_sorted":["cs.LG","cs.NE","eess.IV","stat.ML"],"title_canon_sha256":"f2ed12120ecd672c60128f3edc82a62879259739ab594487e9a56bb4ff100f45","abstract_canon_sha256":"cf42a794790ab103d18072ac3461a227ac12d191ee08ac368b7aa79130813d39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:12.729000Z","signature_b64":"Wnzkpboi8X8C9mC6r8oyV7H0QIAJHbzItZSZbLJBEISZ+NaQpUAQ3ZDHKEb5MWy7ja/nZqsbKkQsFASXHOgFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c51b328bb9af5b87257ca44a39e220a9d0317ced75b599f455c62865cfd891e","last_reissued_at":"2026-07-05T03:39:12.728547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:12.728547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Image Reconstruction using Deep Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Daniel Moyer, Polina Golland, Razvan V Marinescu","submitted_at":"2020-12-08T17:11:26Z","abstract_excerpt":"Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images. However, these end-to-end approaches require re-training every time there is a distribution shift in the inputs (e.g., night images vs daylight) or relevant latent variables (e.g., camera blur or hand motion). In this work, we leverage state-of-the-art (SOTA) generative models (here StyleGAN2) for building powerful image priors, which enable application of Bayes' "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04567","kind":"arxiv","version":5},"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/2012.04567/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":"2012.04567","created_at":"2026-07-05T03:39:12.728599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04567v5","created_at":"2026-07-05T03:39:12.728599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04567","created_at":"2026-07-05T03:39:12.728599+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRI3GKF3TL23","created_at":"2026-07-05T03:39:12.728599+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRI3GKF3TL23Q4SX","created_at":"2026-07-05T03:39:12.728599+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRI3GKF3","created_at":"2026-07-05T03:39:12.728599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18532","citing_title":"COT-AD: Cotton Analysis Dataset","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK","json":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK.json","graph_json":"https://pith.science/api/pith-number/RRI3GKF3TL23Q4SXZJCKHHRCBK/graph.json","events_json":"https://pith.science/api/pith-number/RRI3GKF3TL23Q4SXZJCKHHRCBK/events.json","paper":"https://pith.science/paper/RRI3GKF3"},"agent_actions":{"view_html":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK","download_json":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK.json","view_paper":"https://pith.science/paper/RRI3GKF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04567&json=true","fetch_graph":"https://pith.science/api/pith-number/RRI3GKF3TL23Q4SXZJCKHHRCBK/graph.json","fetch_events":"https://pith.science/api/pith-number/RRI3GKF3TL23Q4SXZJCKHHRCBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK/action/storage_attestation","attest_author":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK/action/author_attestation","sign_citation":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK/action/citation_signature","submit_replication":"https://pith.science/pith/RRI3GKF3TL23Q4SXZJCKHHRCBK/action/replication_record"}},"created_at":"2026-07-05T03:39:12.728599+00:00","updated_at":"2026-07-05T03:39:12.728599+00:00"}