{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XANGQL35DTMQLNKIFUKJMCXGQ5","short_pith_number":"pith:XANGQL35","schema_version":"1.0","canonical_sha256":"b81a682f7d1cd905b5482d14960ae687775c68e4d08517809502de7d47daf044","source":{"kind":"arxiv","id":"2406.04295","version":2},"attestation_state":"computed","paper":{"title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoqun Du, Chunjiang Ge, Gao Huang, Humphrey Shi, Jiayi Guo, Junhao Zhao, Shiji Song, Yulin Wang, Zanlin Ni","submitted_at":"2024-06-06T17:39:09Z","abstract_excerpt":"Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data. The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain. However, in thi"},"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":"2406.04295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:39:09Z","cross_cats_sorted":[],"title_canon_sha256":"ba573a2b1fbf102f1803a5fa68099f9ee102a5ab71797c129430c14c5cdeed16","abstract_canon_sha256":"b9662e0de2b861c40c1afaefa21813b9d5ee847745e197d456af312d8ab7d99c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:05.996209Z","signature_b64":"IuCToo87qEslPUaOO0mxvYgQM5MvKOKmXLJVx6y3OpGMP3MJsURI7Guj/8fvt/A5p6X9fbfj/KkrCVMlBK3tDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81a682f7d1cd905b5482d14960ae687775c68e4d08517809502de7d47daf044","last_reissued_at":"2026-07-05T09:49:05.995759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:05.995759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoqun Du, Chunjiang Ge, Gao Huang, Humphrey Shi, Jiayi Guo, Junhao Zhao, Shiji Song, Yulin Wang, Zanlin Ni","submitted_at":"2024-06-06T17:39:09Z","abstract_excerpt":"Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model performance sensitive to the amount and order of target data. The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain. However, in thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04295","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/2406.04295/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":"2406.04295","created_at":"2026-07-05T09:49:05.995824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04295v2","created_at":"2026-07-05T09:49:05.995824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04295","created_at":"2026-07-05T09:49:05.995824+00:00"},{"alias_kind":"pith_short_12","alias_value":"XANGQL35DTMQ","created_at":"2026-07-05T09:49:05.995824+00:00"},{"alias_kind":"pith_short_16","alias_value":"XANGQL35DTMQLNKI","created_at":"2026-07-05T09:49:05.995824+00:00"},{"alias_kind":"pith_short_8","alias_value":"XANGQL35","created_at":"2026-07-05T09:49:05.995824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16384","citing_title":"Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5","json":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5.json","graph_json":"https://pith.science/api/pith-number/XANGQL35DTMQLNKIFUKJMCXGQ5/graph.json","events_json":"https://pith.science/api/pith-number/XANGQL35DTMQLNKIFUKJMCXGQ5/events.json","paper":"https://pith.science/paper/XANGQL35"},"agent_actions":{"view_html":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5","download_json":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5.json","view_paper":"https://pith.science/paper/XANGQL35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04295&json=true","fetch_graph":"https://pith.science/api/pith-number/XANGQL35DTMQLNKIFUKJMCXGQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/XANGQL35DTMQLNKIFUKJMCXGQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5/action/storage_attestation","attest_author":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5/action/author_attestation","sign_citation":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5/action/citation_signature","submit_replication":"https://pith.science/pith/XANGQL35DTMQLNKIFUKJMCXGQ5/action/replication_record"}},"created_at":"2026-07-05T09:49:05.995824+00:00","updated_at":"2026-07-05T09:49:05.995824+00:00"}