{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PNWG2PGN7S7G4APKVNPNAGH474","short_pith_number":"pith:PNWG2PGN","schema_version":"1.0","canonical_sha256":"7b6c6d3ccdfcbe6e01eaab5ed018fcff25de1aeab74d2e47934783b801ea605c","source":{"kind":"arxiv","id":"2404.18928","version":1},"attestation_state":"computed","paper":{"title":"Stylus: Automatic Adapter Selection for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brandon Trabucco, Ion Stoica, Joseph E. Gonzalez, Justin Wong, Michael Luo, Ruslan Salakhutdinov, Yanping Huang, Zhifeng Chen","submitted_at":"2024-04-29T17:59:16Z","abstract_excerpt":"Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities, accumulating a database of over 100K adapters-most of which are highly customized with insufficient descriptions. This paper explores the problem of matching the prompt to a set of relevant adapters, built on recent work that highlight the performance gains of composing adapters. We introduce Stylus, which efficiently selects and automatically composes task-specif"},"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":"2404.18928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-29T17:59:16Z","cross_cats_sorted":["cs.AI","cs.CL","cs.GR","cs.LG"],"title_canon_sha256":"aff2446b5a4b01dad70f83016b945e866a6d5b16a9f9b31660065ba0a1a2d344","abstract_canon_sha256":"483b8a5bced070d6fb5a48877c907e8fd0d276dad0a46f96ef6e2a7358fb92e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:22.463187Z","signature_b64":"KRwHswevPEkPtuzOlDuiqkdVG0zR/Ca3AA1c0p7sRrizZiuWn19lZWeSy31P+xPNV6z02DHv0rizVfCHOvj5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6c6d3ccdfcbe6e01eaab5ed018fcff25de1aeab74d2e47934783b801ea605c","last_reissued_at":"2026-07-05T08:13:22.462771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:22.462771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stylus: Automatic Adapter Selection for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brandon Trabucco, Ion Stoica, Joseph E. Gonzalez, Justin Wong, Michael Luo, Ruslan Salakhutdinov, Yanping Huang, Zhifeng Chen","submitted_at":"2024-04-29T17:59:16Z","abstract_excerpt":"Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities, accumulating a database of over 100K adapters-most of which are highly customized with insufficient descriptions. This paper explores the problem of matching the prompt to a set of relevant adapters, built on recent work that highlight the performance gains of composing adapters. We introduce Stylus, which efficiently selects and automatically composes task-specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18928","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/2404.18928/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":"2404.18928","created_at":"2026-07-05T08:13:22.462826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18928v1","created_at":"2026-07-05T08:13:22.462826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18928","created_at":"2026-07-05T08:13:22.462826+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNWG2PGN7S7G","created_at":"2026-07-05T08:13:22.462826+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNWG2PGN7S7G4APK","created_at":"2026-07-05T08:13:22.462826+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNWG2PGN","created_at":"2026-07-05T08:13:22.462826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09619","citing_title":"Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474","json":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474.json","graph_json":"https://pith.science/api/pith-number/PNWG2PGN7S7G4APKVNPNAGH474/graph.json","events_json":"https://pith.science/api/pith-number/PNWG2PGN7S7G4APKVNPNAGH474/events.json","paper":"https://pith.science/paper/PNWG2PGN"},"agent_actions":{"view_html":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474","download_json":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474.json","view_paper":"https://pith.science/paper/PNWG2PGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18928&json=true","fetch_graph":"https://pith.science/api/pith-number/PNWG2PGN7S7G4APKVNPNAGH474/graph.json","fetch_events":"https://pith.science/api/pith-number/PNWG2PGN7S7G4APKVNPNAGH474/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474/action/storage_attestation","attest_author":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474/action/author_attestation","sign_citation":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474/action/citation_signature","submit_replication":"https://pith.science/pith/PNWG2PGN7S7G4APKVNPNAGH474/action/replication_record"}},"created_at":"2026-07-05T08:13:22.462826+00:00","updated_at":"2026-07-05T08:13:22.462826+00:00"}