{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7JBGJEJGODCSZ6RSI4FAOGIKNP","short_pith_number":"pith:7JBGJEJG","schema_version":"1.0","canonical_sha256":"fa4264912670c52cfa32470a07190a6bebaea47028a1169fdd24a6c7a237b11d","source":{"kind":"arxiv","id":"2003.13525","version":1},"attestation_state":"computed","paper":{"title":"Improving out-of-distribution generalization via multi-task self-supervised pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Isabela Albuquerque, Junnan Li, Nikhil Naik, Nitish Keskar, Richard Socher","submitted_at":"2020-03-30T14:55:53Z","abstract_excerpt":"Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better than, supervised learning for domain generalization in computer vision. We introduce a new self-supervised pretext task of predicting responses to Gabor filter banks and demonstrate that multi-task learning of compatible pretext tasks improves domain generalization performance as compared to training individual tasks alone. Features learnt through self-supervi"},"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":"2003.13525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T14:55:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d0f84b8fc7c093d37148ac0a3a480efffe97099361a374ccba4fd8fa6ffaf9d0","abstract_canon_sha256":"f5a1579fc4d93b2c132f46f1a61925900463eab101937b7c23777a6d0e9c0b3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:23.872912Z","signature_b64":"MRzgXQNY4C098dx3X1GdEdiEzwgjQ9/lQeNLtYel47XwUOca+AvNN1kqz9ST+uqpLeAaUYT2DIt3Gi0IJ096DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4264912670c52cfa32470a07190a6bebaea47028a1169fdd24a6c7a237b11d","last_reissued_at":"2026-07-05T00:51:23.872358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:23.872358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving out-of-distribution generalization via multi-task self-supervised pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Isabela Albuquerque, Junnan Li, Nikhil Naik, Nitish Keskar, Richard Socher","submitted_at":"2020-03-30T14:55:53Z","abstract_excerpt":"Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better than, supervised learning for domain generalization in computer vision. We introduce a new self-supervised pretext task of predicting responses to Gabor filter banks and demonstrate that multi-task learning of compatible pretext tasks improves domain generalization performance as compared to training individual tasks alone. Features learnt through self-supervi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13525","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/2003.13525/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":"2003.13525","created_at":"2026-07-05T00:51:23.872414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.13525v1","created_at":"2026-07-05T00:51:23.872414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13525","created_at":"2026-07-05T00:51:23.872414+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JBGJEJGODCS","created_at":"2026-07-05T00:51:23.872414+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JBGJEJGODCSZ6RS","created_at":"2026-07-05T00:51:23.872414+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JBGJEJG","created_at":"2026-07-05T00:51:23.872414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02509","citing_title":"Rapidly deploying on-device eye tracking by distilling visual foundation models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP","json":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP.json","graph_json":"https://pith.science/api/pith-number/7JBGJEJGODCSZ6RSI4FAOGIKNP/graph.json","events_json":"https://pith.science/api/pith-number/7JBGJEJGODCSZ6RSI4FAOGIKNP/events.json","paper":"https://pith.science/paper/7JBGJEJG"},"agent_actions":{"view_html":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP","download_json":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP.json","view_paper":"https://pith.science/paper/7JBGJEJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.13525&json=true","fetch_graph":"https://pith.science/api/pith-number/7JBGJEJGODCSZ6RSI4FAOGIKNP/graph.json","fetch_events":"https://pith.science/api/pith-number/7JBGJEJGODCSZ6RSI4FAOGIKNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP/action/storage_attestation","attest_author":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP/action/author_attestation","sign_citation":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP/action/citation_signature","submit_replication":"https://pith.science/pith/7JBGJEJGODCSZ6RSI4FAOGIKNP/action/replication_record"}},"created_at":"2026-07-05T00:51:23.872414+00:00","updated_at":"2026-07-05T00:51:23.872414+00:00"}