{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XWRM3DS2WCDD25L5KOT5PW2FYZ","short_pith_number":"pith:XWRM3DS2","schema_version":"1.0","canonical_sha256":"bda2cd8e5ab0863d757d53a7d7db45c656640adb6c3cb9bfed1b96cbb2edbd64","source":{"kind":"arxiv","id":"1503.06944","version":3},"attestation_state":"computed","paper":{"title":"PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amaury Habrard (LHC), Emilie Morvant (LHC), Fran\\c{c}ois Laviolette, Pascal Germain (SIERRA)","submitted_at":"2015-03-24T08:17:44Z","abstract_excerpt":"In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand, we propose an improvement of the previous approach proposed by Germain et al. (2013), that relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter PAC-Bayesian domain adaptation bound for the stochastic Gibbs classifier. We specialize it to linear classifiers, and design a learning algorithm which "},"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":"1503.06944","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-03-24T08:17:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd299eebd1cbd05838ecb7937168b2068783688ded32b43d193b3ce24c1618e5","abstract_canon_sha256":"e38763ede5d985ee3dd44fefc73e648c1a31ae3c3c613e5a47f472b05b7daf78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:36.940271Z","signature_b64":"zvuvqQHhskBR9QCHB1L5d/ds8OvzOU8u1cPifaLZK9vWhNWBJqziIUwiRWuz/d42IX6UeVzESg4GpzYrqV4ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bda2cd8e5ab0863d757d53a7d7db45c656640adb6c3cb9bfed1b96cbb2edbd64","last_reissued_at":"2026-05-18T01:09:36.939780Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:36.939780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amaury Habrard (LHC), Emilie Morvant (LHC), Fran\\c{c}ois Laviolette, Pascal Germain (SIERRA)","submitted_at":"2015-03-24T08:17:44Z","abstract_excerpt":"In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand, we propose an improvement of the previous approach proposed by Germain et al. (2013), that relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter PAC-Bayesian domain adaptation bound for the stochastic Gibbs classifier. We specialize it to linear classifiers, and design a learning algorithm which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.06944","kind":"arxiv","version":3},"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":"1503.06944","created_at":"2026-05-18T01:09:36.939858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.06944v3","created_at":"2026-05-18T01:09:36.939858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.06944","created_at":"2026-05-18T01:09:36.939858+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWRM3DS2WCDD","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWRM3DS2WCDD25L5","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWRM3DS2","created_at":"2026-05-18T12:29:50.041715+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/XWRM3DS2WCDD25L5KOT5PW2FYZ","json":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ.json","graph_json":"https://pith.science/api/pith-number/XWRM3DS2WCDD25L5KOT5PW2FYZ/graph.json","events_json":"https://pith.science/api/pith-number/XWRM3DS2WCDD25L5KOT5PW2FYZ/events.json","paper":"https://pith.science/paper/XWRM3DS2"},"agent_actions":{"view_html":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ","download_json":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ.json","view_paper":"https://pith.science/paper/XWRM3DS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.06944&json=true","fetch_graph":"https://pith.science/api/pith-number/XWRM3DS2WCDD25L5KOT5PW2FYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XWRM3DS2WCDD25L5KOT5PW2FYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ/action/storage_attestation","attest_author":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ/action/author_attestation","sign_citation":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ/action/citation_signature","submit_replication":"https://pith.science/pith/XWRM3DS2WCDD25L5KOT5PW2FYZ/action/replication_record"}},"created_at":"2026-05-18T01:09:36.939858+00:00","updated_at":"2026-05-18T01:09:36.939858+00:00"}