{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:COUGGLPVHYAWDZD5RRGH2WL2CZ","short_pith_number":"pith:COUGGLPV","schema_version":"1.0","canonical_sha256":"13a8632df53e0161e47d8c4c7d597a166d4f563c5e66853e32091fcda607e745","source":{"kind":"arxiv","id":"1809.02256","version":2},"attestation_state":"computed","paper":{"title":"Multi-Source Domain Adaptation with Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Darsh J Shah, Jiang Guo, Regina Barzilay","submitted_at":"2018-09-07T00:01:42Z","abstract_excerpt":"We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer."},"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":"1809.02256","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T00:01:42Z","cross_cats_sorted":[],"title_canon_sha256":"5d0fd6dfe63e614030183bc7d4107561ffa22d21d710cd28fb3d889937fb5f3c","abstract_canon_sha256":"e7a28579542ce00dd45d322617b3988e365d86b37c8211eacd664d9160b5791f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:15.014269Z","signature_b64":"FNWVMQR3Gv9AaCJwMHhbp9ODHYzqWZnM/+L6e6lDDYECMbfZxDHRRalo98WmZnHWYAu14upN5maCOzCmDyYGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a8632df53e0161e47d8c4c7d597a166d4f563c5e66853e32091fcda607e745","last_reissued_at":"2026-05-18T00:03:15.013691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:15.013691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Source Domain Adaptation with Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Darsh J Shah, Jiang Guo, Regina Barzilay","submitted_at":"2018-09-07T00:01:42Z","abstract_excerpt":"We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02256","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":""},"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":"1809.02256","created_at":"2026-05-18T00:03:15.013783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02256v2","created_at":"2026-05-18T00:03:15.013783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02256","created_at":"2026-05-18T00:03:15.013783+00:00"},{"alias_kind":"pith_short_12","alias_value":"COUGGLPVHYAW","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"COUGGLPVHYAWDZD5","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"COUGGLPV","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":204,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20824","citing_title":"Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ","json":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ.json","graph_json":"https://pith.science/api/pith-number/COUGGLPVHYAWDZD5RRGH2WL2CZ/graph.json","events_json":"https://pith.science/api/pith-number/COUGGLPVHYAWDZD5RRGH2WL2CZ/events.json","paper":"https://pith.science/paper/COUGGLPV"},"agent_actions":{"view_html":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ","download_json":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ.json","view_paper":"https://pith.science/paper/COUGGLPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02256&json=true","fetch_graph":"https://pith.science/api/pith-number/COUGGLPVHYAWDZD5RRGH2WL2CZ/graph.json","fetch_events":"https://pith.science/api/pith-number/COUGGLPVHYAWDZD5RRGH2WL2CZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ/action/storage_attestation","attest_author":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ/action/author_attestation","sign_citation":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ/action/citation_signature","submit_replication":"https://pith.science/pith/COUGGLPVHYAWDZD5RRGH2WL2CZ/action/replication_record"}},"created_at":"2026-05-18T00:03:15.013783+00:00","updated_at":"2026-05-18T00:03:15.013783+00:00"}