{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3A2LH74QPYMJU4OUDLGA3GEZBE","short_pith_number":"pith:3A2LH74Q","schema_version":"1.0","canonical_sha256":"d834b3ff907e189a71d41acc0d98990927e03a0440e41adb0778100774cb2dcb","source":{"kind":"arxiv","id":"2508.10993","version":1},"attestation_state":"computed","paper":{"title":"Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Basile Lewandowski, Lydia Y. Chen, Robert Birke","submitted_at":"2025-08-14T18:00:50Z","abstract_excerpt":"Text-to-image (T2I) models based on diffusion and transformer architectures advance rapidly. They are often pretrained on large corpora, and openly shared on a model platform, such as HuggingFace. Users can then build up AI applications, e.g., generating media contents, by adopting pretrained T2I models and fine-tuning them on the target dataset. While public pretrained T2I models facilitate the democratization of the models, users face a new challenge: which model can be best fine-tuned based on the target data domain? Model selection is well addressed in classification tasks, but little is k"},"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":"2508.10993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:00:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"ebd1b5d45c19e692ca8dba90a21a47e94beccf15db743559c132f5996c37df47","abstract_canon_sha256":"20e18e316c3f04730299c0757085521d62730bdca909cd9317395060b39a0126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:16.507309Z","signature_b64":"X/n1cxPSHgMbNfeK5ukyCTSKqauYE4CUjR4VZdRCbfu8OimbCtBvAnJshEWvY2M4p6SakwcuqH/1VM9ooqaZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d834b3ff907e189a71d41acc0d98990927e03a0440e41adb0778100774cb2dcb","last_reissued_at":"2026-07-05T11:54:16.506839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:16.506839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Basile Lewandowski, Lydia Y. Chen, Robert Birke","submitted_at":"2025-08-14T18:00:50Z","abstract_excerpt":"Text-to-image (T2I) models based on diffusion and transformer architectures advance rapidly. They are often pretrained on large corpora, and openly shared on a model platform, such as HuggingFace. Users can then build up AI applications, e.g., generating media contents, by adopting pretrained T2I models and fine-tuning them on the target dataset. While public pretrained T2I models facilitate the democratization of the models, users face a new challenge: which model can be best fine-tuned based on the target data domain? Model selection is well addressed in classification tasks, but little is k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10993","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/2508.10993/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":"2508.10993","created_at":"2026-07-05T11:54:16.506895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10993v1","created_at":"2026-07-05T11:54:16.506895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10993","created_at":"2026-07-05T11:54:16.506895+00:00"},{"alias_kind":"pith_short_12","alias_value":"3A2LH74QPYMJ","created_at":"2026-07-05T11:54:16.506895+00:00"},{"alias_kind":"pith_short_16","alias_value":"3A2LH74QPYMJU4OU","created_at":"2026-07-05T11:54:16.506895+00:00"},{"alias_kind":"pith_short_8","alias_value":"3A2LH74Q","created_at":"2026-07-05T11:54:16.506895+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/3A2LH74QPYMJU4OUDLGA3GEZBE","json":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE.json","graph_json":"https://pith.science/api/pith-number/3A2LH74QPYMJU4OUDLGA3GEZBE/graph.json","events_json":"https://pith.science/api/pith-number/3A2LH74QPYMJU4OUDLGA3GEZBE/events.json","paper":"https://pith.science/paper/3A2LH74Q"},"agent_actions":{"view_html":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE","download_json":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE.json","view_paper":"https://pith.science/paper/3A2LH74Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10993&json=true","fetch_graph":"https://pith.science/api/pith-number/3A2LH74QPYMJU4OUDLGA3GEZBE/graph.json","fetch_events":"https://pith.science/api/pith-number/3A2LH74QPYMJU4OUDLGA3GEZBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE/action/storage_attestation","attest_author":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE/action/author_attestation","sign_citation":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE/action/citation_signature","submit_replication":"https://pith.science/pith/3A2LH74QPYMJU4OUDLGA3GEZBE/action/replication_record"}},"created_at":"2026-07-05T11:54:16.506895+00:00","updated_at":"2026-07-05T11:54:16.506895+00:00"}