{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQ6KWFCLUQACK6K3XEWKRAU3WD","short_pith_number":"pith:HQ6KWFCL","schema_version":"1.0","canonical_sha256":"3c3cab144ba40025795bb92ca8829bb0edc951249844fa4795ba0dc0dcae02df","source":{"kind":"arxiv","id":"2303.18181","version":2},"attestation_state":"computed","paper":{"title":"A Closer Look at Parameter-Efficient Tuning in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chongxuan Li, Fan Bao, Hang Su, Jun Zhu","submitted_at":"2023-03-31T16:23:29Z","abstract_excerpt":"Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language processing, we investigate parameter-efficient tuning in large diffusion models by inserting small learnable modules (termed adapters). In particular, we decompose the design space of adapters into orthogonal factors -- the input position, the output position as well as the function form, and perform Analysis of Variance (ANOVA), a classical statistical appr"},"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":"2303.18181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-31T16:23:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f704512965da5d70abd99e298ee18c60683cbcb86b2ac4d2e2f74984902c804","abstract_canon_sha256":"3bd7a1a36f2a461c8bb701242bebe7cd9eb2b245296a54c03cb5ad49abc89ae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:17.177638Z","signature_b64":"BOv6i0gTtLq+xT4ptDBpqvbCx0XZIrNX+/NnlyJGKNqt3+KuEUrLJ4BSeYj50qEfe6pU+8vIN4JzIenQ+vDNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c3cab144ba40025795bb92ca8829bb0edc951249844fa4795ba0dc0dcae02df","last_reissued_at":"2026-07-05T06:00:17.177215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:17.177215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Parameter-Efficient Tuning in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chongxuan Li, Fan Bao, Hang Su, Jun Zhu","submitted_at":"2023-03-31T16:23:29Z","abstract_excerpt":"Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language processing, we investigate parameter-efficient tuning in large diffusion models by inserting small learnable modules (termed adapters). In particular, we decompose the design space of adapters into orthogonal factors -- the input position, the output position as well as the function form, and perform Analysis of Variance (ANOVA), a classical statistical appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.18181","kind":"arxiv","version":2},"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/2303.18181/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":"2303.18181","created_at":"2026-07-05T06:00:17.177276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.18181v2","created_at":"2026-07-05T06:00:17.177276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.18181","created_at":"2026-07-05T06:00:17.177276+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQ6KWFCLUQAC","created_at":"2026-07-05T06:00:17.177276+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQ6KWFCLUQACK6K3","created_at":"2026-07-05T06:00:17.177276+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQ6KWFCL","created_at":"2026-07-05T06:00:17.177276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD","json":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD.json","graph_json":"https://pith.science/api/pith-number/HQ6KWFCLUQACK6K3XEWKRAU3WD/graph.json","events_json":"https://pith.science/api/pith-number/HQ6KWFCLUQACK6K3XEWKRAU3WD/events.json","paper":"https://pith.science/paper/HQ6KWFCL"},"agent_actions":{"view_html":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD","download_json":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD.json","view_paper":"https://pith.science/paper/HQ6KWFCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.18181&json=true","fetch_graph":"https://pith.science/api/pith-number/HQ6KWFCLUQACK6K3XEWKRAU3WD/graph.json","fetch_events":"https://pith.science/api/pith-number/HQ6KWFCLUQACK6K3XEWKRAU3WD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD/action/storage_attestation","attest_author":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD/action/author_attestation","sign_citation":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD/action/citation_signature","submit_replication":"https://pith.science/pith/HQ6KWFCLUQACK6K3XEWKRAU3WD/action/replication_record"}},"created_at":"2026-07-05T06:00:17.177276+00:00","updated_at":"2026-07-05T06:00:17.177276+00:00"}