{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:47LXTM7YIUUI7L5ZBMZ5YAAKMB","short_pith_number":"pith:47LXTM7Y","schema_version":"1.0","canonical_sha256":"e7d779b3f845288fafb90b33dc000a60566191038996f1b18a56c909903aed4d","source":{"kind":"arxiv","id":"2010.07539","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Domain Adaptation with Consistency Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"B. Dai, D. Zhao, J. Xu, L. Wang, L. Xiao, Y. Nie, Z. Wang","submitted_at":"2020-10-15T06:03:47Z","abstract_excerpt":"We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transformation (specifically, image rotation) and ask the learner to predict the properties of the transformation. However, the obtained feature representation may contain a large amount of irrelevant information with respect to the main task. To provide further guidance, we force the feature representation of the augmented data to be consistent with tha"},"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":"2010.07539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T06:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"7926120b1318616a01d8103556ee0e009249f049da3d289cf653087d57d74d55","abstract_canon_sha256":"a719546f715e40c7a525fddc88d35b023aef0b7822049584759491bc2210ea42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:18.069899Z","signature_b64":"PPTzRZXuztLmjrRIzK51tef7IDHWdeMz3RSx8UlZGJmrN42SI8wDFSsd4neKhGQcvWcOwepdtOMWUELKqghADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7d779b3f845288fafb90b33dc000a60566191038996f1b18a56c909903aed4d","last_reissued_at":"2026-07-05T01:43:18.069416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:18.069416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Domain Adaptation with Consistency Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"B. Dai, D. Zhao, J. Xu, L. Wang, L. Xiao, Y. Nie, Z. Wang","submitted_at":"2020-10-15T06:03:47Z","abstract_excerpt":"We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transformation (specifically, image rotation) and ask the learner to predict the properties of the transformation. However, the obtained feature representation may contain a large amount of irrelevant information with respect to the main task. To provide further guidance, we force the feature representation of the augmented data to be consistent with tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07539","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/2010.07539/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":"2010.07539","created_at":"2026-07-05T01:43:18.069479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07539v1","created_at":"2026-07-05T01:43:18.069479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07539","created_at":"2026-07-05T01:43:18.069479+00:00"},{"alias_kind":"pith_short_12","alias_value":"47LXTM7YIUUI","created_at":"2026-07-05T01:43:18.069479+00:00"},{"alias_kind":"pith_short_16","alias_value":"47LXTM7YIUUI7L5Z","created_at":"2026-07-05T01:43:18.069479+00:00"},{"alias_kind":"pith_short_8","alias_value":"47LXTM7Y","created_at":"2026-07-05T01:43:18.069479+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/47LXTM7YIUUI7L5ZBMZ5YAAKMB","json":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB.json","graph_json":"https://pith.science/api/pith-number/47LXTM7YIUUI7L5ZBMZ5YAAKMB/graph.json","events_json":"https://pith.science/api/pith-number/47LXTM7YIUUI7L5ZBMZ5YAAKMB/events.json","paper":"https://pith.science/paper/47LXTM7Y"},"agent_actions":{"view_html":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB","download_json":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB.json","view_paper":"https://pith.science/paper/47LXTM7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07539&json=true","fetch_graph":"https://pith.science/api/pith-number/47LXTM7YIUUI7L5ZBMZ5YAAKMB/graph.json","fetch_events":"https://pith.science/api/pith-number/47LXTM7YIUUI7L5ZBMZ5YAAKMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB/action/storage_attestation","attest_author":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB/action/author_attestation","sign_citation":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB/action/citation_signature","submit_replication":"https://pith.science/pith/47LXTM7YIUUI7L5ZBMZ5YAAKMB/action/replication_record"}},"created_at":"2026-07-05T01:43:18.069479+00:00","updated_at":"2026-07-05T01:43:18.069479+00:00"}