{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4PFL6MYUDCARUAA7SUBMJ4YGAG","short_pith_number":"pith:4PFL6MYU","schema_version":"1.0","canonical_sha256":"e3cabf331418811a001f9502c4f30601b8c262a500fb2080d1fd40f234396463","source":{"kind":"arxiv","id":"2311.15841","version":5},"attestation_state":"computed","paper":{"title":"Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Donglin Wang, Siteng Huang, Xi Chen, Yu Liu, Yuqian Fu, Yutong Feng","submitted_at":"2023-11-27T14:07:13Z","abstract_excerpt":"This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled "},"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":"2311.15841","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T14:07:13Z","cross_cats_sorted":[],"title_canon_sha256":"fca00c8307d26c654b86b1e3d90ccd74a7a7e5730586b342fee30c849f743372","abstract_canon_sha256":"f083f180b3b64a5359ef6f7b386bc18bff32cdebc9bd3a3ac2f157d918282565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:29.366343Z","signature_b64":"lytG8BPEMbVq66fwJdrccvl4l5UEQfNWNLUyLnd0LH9LxYtf11PbOYBI+ue10O5OLtFY7UGW9/sK1FCN6EONCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3cabf331418811a001f9502c4f30601b8c262a500fb2080d1fd40f234396463","last_reissued_at":"2026-07-05T08:17:29.365836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:29.365836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Donglin Wang, Siteng Huang, Xi Chen, Yu Liu, Yuqian Fu, Yutong Feng","submitted_at":"2023-11-27T14:07:13Z","abstract_excerpt":"This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15841","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/2311.15841/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":"2311.15841","created_at":"2026-07-05T08:17:29.365896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15841v5","created_at":"2026-07-05T08:17:29.365896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15841","created_at":"2026-07-05T08:17:29.365896+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PFL6MYUDCAR","created_at":"2026-07-05T08:17:29.365896+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PFL6MYUDCARUAA7","created_at":"2026-07-05T08:17:29.365896+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PFL6MYU","created_at":"2026-07-05T08:17:29.365896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05501","citing_title":"Preliminary Explorations with GPT-4o(mni) Native Image Generation","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG","json":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG.json","graph_json":"https://pith.science/api/pith-number/4PFL6MYUDCARUAA7SUBMJ4YGAG/graph.json","events_json":"https://pith.science/api/pith-number/4PFL6MYUDCARUAA7SUBMJ4YGAG/events.json","paper":"https://pith.science/paper/4PFL6MYU"},"agent_actions":{"view_html":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG","download_json":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG.json","view_paper":"https://pith.science/paper/4PFL6MYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15841&json=true","fetch_graph":"https://pith.science/api/pith-number/4PFL6MYUDCARUAA7SUBMJ4YGAG/graph.json","fetch_events":"https://pith.science/api/pith-number/4PFL6MYUDCARUAA7SUBMJ4YGAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG/action/storage_attestation","attest_author":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG/action/author_attestation","sign_citation":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG/action/citation_signature","submit_replication":"https://pith.science/pith/4PFL6MYUDCARUAA7SUBMJ4YGAG/action/replication_record"}},"created_at":"2026-07-05T08:17:29.365896+00:00","updated_at":"2026-07-05T08:17:29.365896+00:00"}