{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UHJ6DFUMB5EENXRX6BOKZBRSWZ","short_pith_number":"pith:UHJ6DFUM","schema_version":"1.0","canonical_sha256":"a1d3e1968c0f4846de37f05cac8632b6516ab1b93b857702668b477e95977a68","source":{"kind":"arxiv","id":"2210.09834","version":1},"attestation_state":"computed","paper":{"title":"Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Corentin Abgrall, Emmanuel Dellandr\\'ea, Gilles H\\'enaff, Liming Chen, Thomas Duboudin (imagine)","submitted_at":"2022-10-17T08:05:38Z","abstract_excerpt":"Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we argue that, to reach further improvements, these approaches should be combined with training procedure modifications aiming to learn a more diverse set of patterns. Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned wi"},"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":"2210.09834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T08:05:38Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"67f7bdad42dffbd5c0b577df774d36470bac7b4e51a53d1ec5f5974e20ed3d4e","abstract_canon_sha256":"441d261a1c5b93a05bd54a28593e98b753cc1181a914b87df7e7f2b51ca872f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:00.062066Z","signature_b64":"QMM1xh5OyXZDHc+byc+6OCijKQLh5pvzmsOHa3EbaR7pMVWP9T9UEweIhB6oYMiditbDcG8QkPU3Fjt+aH1LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d3e1968c0f4846de37f05cac8632b6516ab1b93b857702668b477e95977a68","last_reissued_at":"2026-07-05T05:28:00.061606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:00.061606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Corentin Abgrall, Emmanuel Dellandr\\'ea, Gilles H\\'enaff, Liming Chen, Thomas Duboudin (imagine)","submitted_at":"2022-10-17T08:05:38Z","abstract_excerpt":"Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we argue that, to reach further improvements, these approaches should be combined with training procedure modifications aiming to learn a more diverse set of patterns. Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09834","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/2210.09834/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":"2210.09834","created_at":"2026-07-05T05:28:00.061659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09834v1","created_at":"2026-07-05T05:28:00.061659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09834","created_at":"2026-07-05T05:28:00.061659+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHJ6DFUMB5EE","created_at":"2026-07-05T05:28:00.061659+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHJ6DFUMB5EENXRX","created_at":"2026-07-05T05:28:00.061659+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHJ6DFUM","created_at":"2026-07-05T05:28:00.061659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16160","citing_title":"Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalization","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ","json":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ.json","graph_json":"https://pith.science/api/pith-number/UHJ6DFUMB5EENXRX6BOKZBRSWZ/graph.json","events_json":"https://pith.science/api/pith-number/UHJ6DFUMB5EENXRX6BOKZBRSWZ/events.json","paper":"https://pith.science/paper/UHJ6DFUM"},"agent_actions":{"view_html":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ","download_json":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ.json","view_paper":"https://pith.science/paper/UHJ6DFUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09834&json=true","fetch_graph":"https://pith.science/api/pith-number/UHJ6DFUMB5EENXRX6BOKZBRSWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UHJ6DFUMB5EENXRX6BOKZBRSWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ/action/storage_attestation","attest_author":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ/action/author_attestation","sign_citation":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ/action/citation_signature","submit_replication":"https://pith.science/pith/UHJ6DFUMB5EENXRX6BOKZBRSWZ/action/replication_record"}},"created_at":"2026-07-05T05:28:00.061659+00:00","updated_at":"2026-07-05T05:28:00.061659+00:00"}