{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FFD3OPTDRU2ZO7EVLM6M3FPKF","short_pith_number":"pith:2FFD3OPT","schema_version":"1.0","canonical_sha256":"d14a3db9f31c69acbbe4aad9e66caf51401ca5b05eef4ef27f614a6f4f3fc58f","source":{"kind":"arxiv","id":"2410.03263","version":2},"attestation_state":"computed","paper":{"title":"Test-time Adaptation for Regression by Subspace Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Atsutoshi Kumagai, Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami","submitted_at":"2024-10-04T09:31:10Z","abstract_excerpt":"This paper investigates test-time adaptation (TTA) for regression, where a regression model pre-trained in a source domain is adapted to an unknown target distribution with unlabeled target data. Although regression is one of the fundamental tasks in machine learning, most of the existing TTA methods have classification-specific designs, which assume that models output class-categorical predictions, whereas regression models typically output only single scalar values. To enable TTA for regression, we adopt a feature alignment approach, which aligns the feature distributions between the source "},"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":"2410.03263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:31:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"430b78ba3cd76acb703421b4b51062f45c4c0eed026f84f04c61621f64765122","abstract_canon_sha256":"31845afdc2a37a33f196a8fce3ac57fbb11a923e240aaa351f7ebf9789905383"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:18.223889Z","signature_b64":"3pwVN+llfI6ecVT486pdEvHUM/y8BLEBRZY2X8oj18/nMjQvHjvKL41M1KIssnnJSE5oBayp0OWkHKUtzvA6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d14a3db9f31c69acbbe4aad9e66caf51401ca5b05eef4ef27f614a6f4f3fc58f","last_reissued_at":"2026-07-05T10:04:18.223402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:18.223402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-time Adaptation for Regression by Subspace Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Atsutoshi Kumagai, Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami","submitted_at":"2024-10-04T09:31:10Z","abstract_excerpt":"This paper investigates test-time adaptation (TTA) for regression, where a regression model pre-trained in a source domain is adapted to an unknown target distribution with unlabeled target data. Although regression is one of the fundamental tasks in machine learning, most of the existing TTA methods have classification-specific designs, which assume that models output class-categorical predictions, whereas regression models typically output only single scalar values. To enable TTA for regression, we adopt a feature alignment approach, which aligns the feature distributions between the source "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03263","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/2410.03263/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":"2410.03263","created_at":"2026-07-05T10:04:18.223461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03263v2","created_at":"2026-07-05T10:04:18.223461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03263","created_at":"2026-07-05T10:04:18.223461+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FFD3OPTDRU2","created_at":"2026-07-05T10:04:18.223461+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FFD3OPTDRU2ZO7E","created_at":"2026-07-05T10:04:18.223461+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FFD3OPT","created_at":"2026-07-05T10:04:18.223461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04153","citing_title":"Uncertainty-Aware Test-Time Adaptation for Cross-Region Spatio-Temporal Fusion of Land Surface Temperature","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF","json":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF.json","graph_json":"https://pith.science/api/pith-number/2FFD3OPTDRU2ZO7EVLM6M3FPKF/graph.json","events_json":"https://pith.science/api/pith-number/2FFD3OPTDRU2ZO7EVLM6M3FPKF/events.json","paper":"https://pith.science/paper/2FFD3OPT"},"agent_actions":{"view_html":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF","download_json":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF.json","view_paper":"https://pith.science/paper/2FFD3OPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03263&json=true","fetch_graph":"https://pith.science/api/pith-number/2FFD3OPTDRU2ZO7EVLM6M3FPKF/graph.json","fetch_events":"https://pith.science/api/pith-number/2FFD3OPTDRU2ZO7EVLM6M3FPKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF/action/storage_attestation","attest_author":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF/action/author_attestation","sign_citation":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF/action/citation_signature","submit_replication":"https://pith.science/pith/2FFD3OPTDRU2ZO7EVLM6M3FPKF/action/replication_record"}},"created_at":"2026-07-05T10:04:18.223461+00:00","updated_at":"2026-07-05T10:04:18.223461+00:00"}