{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFWHWYHZVN7KRBA5G5MYLJBBDE","short_pith_number":"pith:RFWHWYHZ","schema_version":"1.0","canonical_sha256":"896c7b60f9ab7ea8841d375985a421190fc7e02b371e3bef60caa6bdd4566ca6","source":{"kind":"arxiv","id":"2405.16819","version":1},"attestation_state":"computed","paper":{"title":"Automatic Domain Adaptation by Transformers in In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kota Matsui, Masaaki Imaizumi, Ryuichiro Hataya","submitted_at":"2024-05-27T04:33:53Z","abstract_excerpt":"Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and opt for domain adaptation methods for a given dataset in the in-context learning framework, where a foundation model performs new tasks without updating its parameters at test time. Specifically, we prove that Transformers can approximate instance-based and feature-based unsupervised domain adaptation algorithms and automatically select an algorithm suited for a given dataset. Numerical results indicate that in-cont"},"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":"2405.16819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T04:33:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ce43d0d97b67236072f38fc7693ff63581c6265acfa02578a609fe6a0e740fd","abstract_canon_sha256":"e377a51063f03598e7690b45f988373ac37e8b22771e6456cd74aec3486a07a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:35.972427Z","signature_b64":"Uh8mcLlCIFit/qQUYJ8A0J+u3Hy8luw2faKw8b0nWaoZl22M5/sxkRdF2v+lp81O5nv0nHFjv0vYx1+NyBgiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"896c7b60f9ab7ea8841d375985a421190fc7e02b371e3bef60caa6bdd4566ca6","last_reissued_at":"2026-07-05T08:23:35.971913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:35.971913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Domain Adaptation by Transformers in In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kota Matsui, Masaaki Imaizumi, Ryuichiro Hataya","submitted_at":"2024-05-27T04:33:53Z","abstract_excerpt":"Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and opt for domain adaptation methods for a given dataset in the in-context learning framework, where a foundation model performs new tasks without updating its parameters at test time. Specifically, we prove that Transformers can approximate instance-based and feature-based unsupervised domain adaptation algorithms and automatically select an algorithm suited for a given dataset. Numerical results indicate that in-cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16819","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/2405.16819/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":"2405.16819","created_at":"2026-07-05T08:23:35.971982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16819v1","created_at":"2026-07-05T08:23:35.971982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16819","created_at":"2026-07-05T08:23:35.971982+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFWHWYHZVN7K","created_at":"2026-07-05T08:23:35.971982+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFWHWYHZVN7KRBA5","created_at":"2026-07-05T08:23:35.971982+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFWHWYHZ","created_at":"2026-07-05T08:23:35.971982+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/RFWHWYHZVN7KRBA5G5MYLJBBDE","json":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE.json","graph_json":"https://pith.science/api/pith-number/RFWHWYHZVN7KRBA5G5MYLJBBDE/graph.json","events_json":"https://pith.science/api/pith-number/RFWHWYHZVN7KRBA5G5MYLJBBDE/events.json","paper":"https://pith.science/paper/RFWHWYHZ"},"agent_actions":{"view_html":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE","download_json":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE.json","view_paper":"https://pith.science/paper/RFWHWYHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16819&json=true","fetch_graph":"https://pith.science/api/pith-number/RFWHWYHZVN7KRBA5G5MYLJBBDE/graph.json","fetch_events":"https://pith.science/api/pith-number/RFWHWYHZVN7KRBA5G5MYLJBBDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE/action/storage_attestation","attest_author":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE/action/author_attestation","sign_citation":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE/action/citation_signature","submit_replication":"https://pith.science/pith/RFWHWYHZVN7KRBA5G5MYLJBBDE/action/replication_record"}},"created_at":"2026-07-05T08:23:35.971982+00:00","updated_at":"2026-07-05T08:23:35.971982+00:00"}