{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TF4R4TQ7VQ65525QAAFURDKY35","short_pith_number":"pith:TF4R4TQ7","schema_version":"1.0","canonical_sha256":"99791e4e1fac3ddeebb0000b488d58df6116fa0fa5a0b54d2871883b8fd34a7c","source":{"kind":"arxiv","id":"2505.03667","version":1},"attestation_state":"computed","paper":{"title":"Distribution-Conditional Generation: From Class Distribution to Creative Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Feng, Jing Wang, Xin Geng, Xu Yang, Yucheng Xie","submitted_at":"2025-05-06T16:07:12Z","abstract_excerpt":"Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods typically enhance creativity by combining pairs of known concepts, yielding compositions that, while out-of-distribution, remain linguistically describable and bounded within the existing semantic space. Inspired by the soft probabilistic outputs of classifiers on ambiguous inputs, we propose Distribution-Conditional Generation, a novel formulation that models"},"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":"2505.03667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T16:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"42fd6c69311d43eab36b9e32836a6ce2c44ee32044da075ad3c1b6155369ad29","abstract_canon_sha256":"00bff2f3a14bb0ed359baba4c10c8590f0f4fcc7d590384c18fc448d2988bff0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:20.189182Z","signature_b64":"IDQmIh4NqZWfXGFqZjkViQbuK9uzz2zbcdQgWAl/Kiqaqye5/FWYV4ADxrNfY7gwQqMYAWJg1fRp/LVE0yvIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99791e4e1fac3ddeebb0000b488d58df6116fa0fa5a0b54d2871883b8fd34a7c","last_reissued_at":"2026-07-05T10:59:20.188706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:20.188706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution-Conditional Generation: From Class Distribution to Creative Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Feng, Jing Wang, Xin Geng, Xu Yang, Yucheng Xie","submitted_at":"2025-05-06T16:07:12Z","abstract_excerpt":"Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods typically enhance creativity by combining pairs of known concepts, yielding compositions that, while out-of-distribution, remain linguistically describable and bounded within the existing semantic space. Inspired by the soft probabilistic outputs of classifiers on ambiguous inputs, we propose Distribution-Conditional Generation, a novel formulation that models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03667","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/2505.03667/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":"2505.03667","created_at":"2026-07-05T10:59:20.188765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03667v1","created_at":"2026-07-05T10:59:20.188765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03667","created_at":"2026-07-05T10:59:20.188765+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF4R4TQ7VQ65","created_at":"2026-07-05T10:59:20.188765+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF4R4TQ7VQ65525Q","created_at":"2026-07-05T10:59:20.188765+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF4R4TQ7","created_at":"2026-07-05T10:59:20.188765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16477","citing_title":"Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35","json":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35.json","graph_json":"https://pith.science/api/pith-number/TF4R4TQ7VQ65525QAAFURDKY35/graph.json","events_json":"https://pith.science/api/pith-number/TF4R4TQ7VQ65525QAAFURDKY35/events.json","paper":"https://pith.science/paper/TF4R4TQ7"},"agent_actions":{"view_html":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35","download_json":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35.json","view_paper":"https://pith.science/paper/TF4R4TQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03667&json=true","fetch_graph":"https://pith.science/api/pith-number/TF4R4TQ7VQ65525QAAFURDKY35/graph.json","fetch_events":"https://pith.science/api/pith-number/TF4R4TQ7VQ65525QAAFURDKY35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35/action/storage_attestation","attest_author":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35/action/author_attestation","sign_citation":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35/action/citation_signature","submit_replication":"https://pith.science/pith/TF4R4TQ7VQ65525QAAFURDKY35/action/replication_record"}},"created_at":"2026-07-05T10:59:20.188765+00:00","updated_at":"2026-07-05T10:59:20.188765+00:00"}