{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O5GRO57XIGFHW3GCWKTCFCC76D","short_pith_number":"pith:O5GRO57X","schema_version":"1.0","canonical_sha256":"774d1777f7418a7b6cc2b2a622885ff0f8de7cb1520ca31429f13fc6acd30be5","source":{"kind":"arxiv","id":"1812.01754","version":4},"attestation_state":"computed","paper":{"title":"Moment Matching for Multi-Source Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Kate Saenko, Qinxun Bai, Xide Xia, Xingchao Peng, Zijun Huang","submitted_at":"2018-12-04T23:43:37Z","abstract_excerpt":"Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning "},"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":"1812.01754","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T23:43:37Z","cross_cats_sorted":[],"title_canon_sha256":"7caa49e5850f29aa9a134536449c72d706803128ec06c0c66098a10a72c49588","abstract_canon_sha256":"bf4d3c2c68cd5c6e58da7033e2d6e422bf513df28de1d0460a15da2ddf53e603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:13.366790Z","signature_b64":"QO0/1YTZfE9xZi/rWP8WggDU9CQMy5SziRkvIgULA9Fyi/V8T6PDvQy1l1EVnWMx4vPBaM57FLIQH4+SqUuUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"774d1777f7418a7b6cc2b2a622885ff0f8de7cb1520ca31429f13fc6acd30be5","last_reissued_at":"2026-07-05T00:00:13.366335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:13.366335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moment Matching for Multi-Source Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Kate Saenko, Qinxun Bai, Xide Xia, Xingchao Peng, Zijun Huang","submitted_at":"2018-12-04T23:43:37Z","abstract_excerpt":"Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01754","kind":"arxiv","version":4},"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/1812.01754/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":"1812.01754","created_at":"2026-07-05T00:00:13.366397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01754v4","created_at":"2026-07-05T00:00:13.366397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01754","created_at":"2026-07-05T00:00:13.366397+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5GRO57XIGFH","created_at":"2026-07-05T00:00:13.366397+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5GRO57XIGFHW3GC","created_at":"2026-07-05T00:00:13.366397+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5GRO57X","created_at":"2026-07-05T00:00:13.366397+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/O5GRO57XIGFHW3GCWKTCFCC76D","json":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D.json","graph_json":"https://pith.science/api/pith-number/O5GRO57XIGFHW3GCWKTCFCC76D/graph.json","events_json":"https://pith.science/api/pith-number/O5GRO57XIGFHW3GCWKTCFCC76D/events.json","paper":"https://pith.science/paper/O5GRO57X"},"agent_actions":{"view_html":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D","download_json":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D.json","view_paper":"https://pith.science/paper/O5GRO57X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01754&json=true","fetch_graph":"https://pith.science/api/pith-number/O5GRO57XIGFHW3GCWKTCFCC76D/graph.json","fetch_events":"https://pith.science/api/pith-number/O5GRO57XIGFHW3GCWKTCFCC76D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D/action/storage_attestation","attest_author":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D/action/author_attestation","sign_citation":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D/action/citation_signature","submit_replication":"https://pith.science/pith/O5GRO57XIGFHW3GCWKTCFCC76D/action/replication_record"}},"created_at":"2026-07-05T00:00:13.366397+00:00","updated_at":"2026-07-05T00:00:13.366397+00:00"}