{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XJS7DYNXEEPXURB26UZ7B6FE4Z","short_pith_number":"pith:XJS7DYNX","schema_version":"1.0","canonical_sha256":"ba65f1e1b7211f7a443af533f0f8a4e6504b28d3b2d468fdf41555e4ab267c01","source":{"kind":"arxiv","id":"2503.12526","version":1},"attestation_state":"computed","paper":{"title":"EditID: Training-Free Editable ID Customization for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guandong Li, Zhaobin Chu","submitted_at":"2025-03-16T14:41:30Z","abstract_excerpt":"We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more on ID consistency while neglecting editability. It is challenging to alter facial orientation, character attributes, and other features through prompts. EditID addresses this by deconstructing the text-to-image model for customized IDs into an image generation branch and a character feature branch. The character feature branch is further decoupled into three modules: feature e"},"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":"2503.12526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T14:41:30Z","cross_cats_sorted":[],"title_canon_sha256":"34b8b8f3d8a66edd316019fe3e724b1ab7e12f0a7fc435d785c64bebc6720877","abstract_canon_sha256":"ea31ba186d2fc6f69ff4846c83b3710b522e693b7f16ff2c314efab15c7640fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:15.516678Z","signature_b64":"eliIDto7X+Oz4ovuzrENhG9z0v1navpIiZeuMAJvcZ6z5+RG037X93Qsa6Vo46ILenXTIUqp3lnfMBMi0Z0sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba65f1e1b7211f7a443af533f0f8a4e6504b28d3b2d468fdf41555e4ab267c01","last_reissued_at":"2026-07-05T10:32:15.516155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:15.516155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EditID: Training-Free Editable ID Customization for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guandong Li, Zhaobin Chu","submitted_at":"2025-03-16T14:41:30Z","abstract_excerpt":"We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more on ID consistency while neglecting editability. It is challenging to alter facial orientation, character attributes, and other features through prompts. EditID addresses this by deconstructing the text-to-image model for customized IDs into an image generation branch and a character feature branch. The character feature branch is further decoupled into three modules: feature e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12526","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/2503.12526/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":"2503.12526","created_at":"2026-07-05T10:32:15.516216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12526v1","created_at":"2026-07-05T10:32:15.516216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12526","created_at":"2026-07-05T10:32:15.516216+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJS7DYNXEEPX","created_at":"2026-07-05T10:32:15.516216+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJS7DYNXEEPXURB2","created_at":"2026-07-05T10:32:15.516216+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJS7DYNX","created_at":"2026-07-05T10:32:15.516216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16492","citing_title":"LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17500","citing_title":"Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z","json":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z.json","graph_json":"https://pith.science/api/pith-number/XJS7DYNXEEPXURB26UZ7B6FE4Z/graph.json","events_json":"https://pith.science/api/pith-number/XJS7DYNXEEPXURB26UZ7B6FE4Z/events.json","paper":"https://pith.science/paper/XJS7DYNX"},"agent_actions":{"view_html":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z","download_json":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z.json","view_paper":"https://pith.science/paper/XJS7DYNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12526&json=true","fetch_graph":"https://pith.science/api/pith-number/XJS7DYNXEEPXURB26UZ7B6FE4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/XJS7DYNXEEPXURB26UZ7B6FE4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z/action/storage_attestation","attest_author":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z/action/author_attestation","sign_citation":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z/action/citation_signature","submit_replication":"https://pith.science/pith/XJS7DYNXEEPXURB26UZ7B6FE4Z/action/replication_record"}},"created_at":"2026-07-05T10:32:15.516216+00:00","updated_at":"2026-07-05T10:32:15.516216+00:00"}