{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AOEG4XIYDN45AXMSE3ZVRJPZKP","short_pith_number":"pith:AOEG4XIY","schema_version":"1.0","canonical_sha256":"03886e5d181b79d05d9226f358a5f953d4221862040f84717d0b0de1745719d8","source":{"kind":"arxiv","id":"2111.15264","version":3},"attestation_state":"computed","paper":{"title":"EdiBERT, a generative model for image editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, J\\'er\\'emie Mary, Thibaut Issenhuth, Ugo Tanielian","submitted_at":"2021-11-30T10:23:06Z","abstract_excerpt":"Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often developed and trained for each specific task, even though many image edition tasks share similarities. In denoising, inpainting, or image compositing, one always aims at generating a realistic image from a low-quality one. In this paper, we aim at making a step towards a unified approach for image editing. To do so, we propose EdiBERT, a bi-directional transformer trained in the discrete latent space built by a vector"},"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":"2111.15264","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T10:23:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2fd571720c7481518bcecd4cdcf6b05de185d3aa20346cfa771e41c5060810b4","abstract_canon_sha256":"ac0b11b00e72d9f660f0aac59ad688ba7075ce67c8f0e1b25c76181a2b2f1a65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:15.391480Z","signature_b64":"Xo5sfG9lDLaC1I5whVBlDSgc6tisoMFdXPzOUTO3DqgXHnQ0SwvAxXdJ5X2Wemn50nehu3ne6XGAsEtPse6TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03886e5d181b79d05d9226f358a5f953d4221862040f84717d0b0de1745719d8","last_reissued_at":"2026-07-05T04:42:15.390845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:15.390845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdiBERT, a generative model for image editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, J\\'er\\'emie Mary, Thibaut Issenhuth, Ugo Tanielian","submitted_at":"2021-11-30T10:23:06Z","abstract_excerpt":"Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often developed and trained for each specific task, even though many image edition tasks share similarities. In denoising, inpainting, or image compositing, one always aims at generating a realistic image from a low-quality one. In this paper, we aim at making a step towards a unified approach for image editing. To do so, we propose EdiBERT, a bi-directional transformer trained in the discrete latent space built by a vector"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15264","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/2111.15264/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":"2111.15264","created_at":"2026-07-05T04:42:15.390912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15264v3","created_at":"2026-07-05T04:42:15.390912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15264","created_at":"2026-07-05T04:42:15.390912+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOEG4XIYDN45","created_at":"2026-07-05T04:42:15.390912+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOEG4XIYDN45AXMS","created_at":"2026-07-05T04:42:15.390912+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOEG4XIY","created_at":"2026-07-05T04:42:15.390912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10281","citing_title":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP","json":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP.json","graph_json":"https://pith.science/api/pith-number/AOEG4XIYDN45AXMSE3ZVRJPZKP/graph.json","events_json":"https://pith.science/api/pith-number/AOEG4XIYDN45AXMSE3ZVRJPZKP/events.json","paper":"https://pith.science/paper/AOEG4XIY"},"agent_actions":{"view_html":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP","download_json":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP.json","view_paper":"https://pith.science/paper/AOEG4XIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15264&json=true","fetch_graph":"https://pith.science/api/pith-number/AOEG4XIYDN45AXMSE3ZVRJPZKP/graph.json","fetch_events":"https://pith.science/api/pith-number/AOEG4XIYDN45AXMSE3ZVRJPZKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP/action/storage_attestation","attest_author":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP/action/author_attestation","sign_citation":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP/action/citation_signature","submit_replication":"https://pith.science/pith/AOEG4XIYDN45AXMSE3ZVRJPZKP/action/replication_record"}},"created_at":"2026-07-05T04:42:15.390912+00:00","updated_at":"2026-07-05T04:42:15.390912+00:00"}