{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4STBG2R6RJA7Y6OW25ZELLYMWC","short_pith_number":"pith:4STBG2R6","schema_version":"1.0","canonical_sha256":"e4a6136a3e8a41fc79d6d77245af0cb08de5eb6f0d34eacf6cc40a8e730c59fb","source":{"kind":"arxiv","id":"2302.00194","version":1},"attestation_state":"computed","paper":{"title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Liang, Liang Wang, Rong Jin, Tieniu Tan, Xue Wang, Yifan Zhang, Zhang Zhang","submitted_at":"2023-02-01T02:55:26Z","abstract_excerpt":"A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features by Domain Adversarial Training (DAT) received widespread attention. Despite its success, we observe training instability from DAT, mostly due to over-confident domain discriminator and environment label noise. To address this issue, we proposed Environment Label Smoothing (ELS), which encourages the discriminator to output soft probability, which thus reduces the confidence of the discriminator and alleviates the imp"},"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":"2302.00194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T02:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"9691fbc8720a3aebefcfad09aa14faef49d84797031f2910a61885b8119726df","abstract_canon_sha256":"f9c49e3b58a9503f407ee6947abe412cbb6aeb3f6ffbb8bf7fe76002d40b0999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:00.675956Z","signature_b64":"GlnzF2haq+e+XREQxg+ndxRg3a2U4Ir0+nUIJ0P2kUTbrxRfPgnp3G5CH70jf3XNBi9qHDGiviN5hKgLqjALBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a6136a3e8a41fc79d6d77245af0cb08de5eb6f0d34eacf6cc40a8e730c59fb","last_reissued_at":"2026-07-05T05:38:00.675527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:00.675527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Liang, Liang Wang, Rong Jin, Tieniu Tan, Xue Wang, Yifan Zhang, Zhang Zhang","submitted_at":"2023-02-01T02:55:26Z","abstract_excerpt":"A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features by Domain Adversarial Training (DAT) received widespread attention. Despite its success, we observe training instability from DAT, mostly due to over-confident domain discriminator and environment label noise. To address this issue, we proposed Environment Label Smoothing (ELS), which encourages the discriminator to output soft probability, which thus reduces the confidence of the discriminator and alleviates the imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00194","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/2302.00194/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":"2302.00194","created_at":"2026-07-05T05:38:00.675595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00194v1","created_at":"2026-07-05T05:38:00.675595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00194","created_at":"2026-07-05T05:38:00.675595+00:00"},{"alias_kind":"pith_short_12","alias_value":"4STBG2R6RJA7","created_at":"2026-07-05T05:38:00.675595+00:00"},{"alias_kind":"pith_short_16","alias_value":"4STBG2R6RJA7Y6OW","created_at":"2026-07-05T05:38:00.675595+00:00"},{"alias_kind":"pith_short_8","alias_value":"4STBG2R6","created_at":"2026-07-05T05:38:00.675595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04949","citing_title":"Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluation","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC","json":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC.json","graph_json":"https://pith.science/api/pith-number/4STBG2R6RJA7Y6OW25ZELLYMWC/graph.json","events_json":"https://pith.science/api/pith-number/4STBG2R6RJA7Y6OW25ZELLYMWC/events.json","paper":"https://pith.science/paper/4STBG2R6"},"agent_actions":{"view_html":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC","download_json":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC.json","view_paper":"https://pith.science/paper/4STBG2R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00194&json=true","fetch_graph":"https://pith.science/api/pith-number/4STBG2R6RJA7Y6OW25ZELLYMWC/graph.json","fetch_events":"https://pith.science/api/pith-number/4STBG2R6RJA7Y6OW25ZELLYMWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC/action/storage_attestation","attest_author":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC/action/author_attestation","sign_citation":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC/action/citation_signature","submit_replication":"https://pith.science/pith/4STBG2R6RJA7Y6OW25ZELLYMWC/action/replication_record"}},"created_at":"2026-07-05T05:38:00.675595+00:00","updated_at":"2026-07-05T05:38:00.675595+00:00"}