{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VONAWWHTKW5VPJVLGL3VOB7IE2","short_pith_number":"pith:VONAWWHT","schema_version":"1.0","canonical_sha256":"ab9a0b58f355bb57a6ab32f75707e826bcd40ce8e07d7e2ae1188d8a8c9a5842","source":{"kind":"arxiv","id":"2102.12037","version":3},"attestation_state":"computed","paper":{"title":"Conditional Image Generation by Conditioning Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Frank Wood, Saeid Naderiparizi, William Harvey","submitted_at":"2021-02-24T02:59:43Z","abstract_excerpt":"We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE. To train the conditional VAE, we only need to train an artifact to perform amortized inference over the unconditional VAE's latent variables given a conditioning input. We demonstrate our approach on tasks including image inpainting, for which it outperforms state-of-the-art GAN-based approaches at faithfully representing the inherent uncertainty."},"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":"2102.12037","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T02:59:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8c1d8bc35f610bae7388263bd6358fcbc70b1ea723edc2e0389aef781674023","abstract_canon_sha256":"68c2970f317c34e6c64fd7017f5f47deee5d3e1ee937d7a757182ef12bc8a383"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:04.861551Z","signature_b64":"dgJmQ+zn8fbBs/u+2E0KVLXFxqx9kL63gBmP8Ll5WIjTxg/5BW6ZiPdkfEdms//537U79Jvxkr8wpNZjRZu/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab9a0b58f355bb57a6ab32f75707e826bcd40ce8e07d7e2ae1188d8a8c9a5842","last_reissued_at":"2026-07-05T04:27:04.861148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:04.861148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Image Generation by Conditioning Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Frank Wood, Saeid Naderiparizi, William Harvey","submitted_at":"2021-02-24T02:59:43Z","abstract_excerpt":"We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE. To train the conditional VAE, we only need to train an artifact to perform amortized inference over the unconditional VAE's latent variables given a conditioning input. We demonstrate our approach on tasks including image inpainting, for which it outperforms state-of-the-art GAN-based approaches at faithfully representing the inherent uncertainty."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12037","kind":"arxiv","version":3},"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/2102.12037/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":"2102.12037","created_at":"2026-07-05T04:27:04.861202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12037v3","created_at":"2026-07-05T04:27:04.861202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12037","created_at":"2026-07-05T04:27:04.861202+00:00"},{"alias_kind":"pith_short_12","alias_value":"VONAWWHTKW5V","created_at":"2026-07-05T04:27:04.861202+00:00"},{"alias_kind":"pith_short_16","alias_value":"VONAWWHTKW5VPJVL","created_at":"2026-07-05T04:27:04.861202+00:00"},{"alias_kind":"pith_short_8","alias_value":"VONAWWHT","created_at":"2026-07-05T04:27:04.861202+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/VONAWWHTKW5VPJVLGL3VOB7IE2","json":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2.json","graph_json":"https://pith.science/api/pith-number/VONAWWHTKW5VPJVLGL3VOB7IE2/graph.json","events_json":"https://pith.science/api/pith-number/VONAWWHTKW5VPJVLGL3VOB7IE2/events.json","paper":"https://pith.science/paper/VONAWWHT"},"agent_actions":{"view_html":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2","download_json":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2.json","view_paper":"https://pith.science/paper/VONAWWHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12037&json=true","fetch_graph":"https://pith.science/api/pith-number/VONAWWHTKW5VPJVLGL3VOB7IE2/graph.json","fetch_events":"https://pith.science/api/pith-number/VONAWWHTKW5VPJVLGL3VOB7IE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2/action/storage_attestation","attest_author":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2/action/author_attestation","sign_citation":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2/action/citation_signature","submit_replication":"https://pith.science/pith/VONAWWHTKW5VPJVLGL3VOB7IE2/action/replication_record"}},"created_at":"2026-07-05T04:27:04.861202+00:00","updated_at":"2026-07-05T04:27:04.861202+00:00"}