{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EFOZ7JMBR3A4PU3J6C6D6Q5UOC","short_pith_number":"pith:EFOZ7JMB","schema_version":"1.0","canonical_sha256":"215d9fa5818ec1c7d369f0bc3f43b470bf0968b5fa27deee922b927553dd6fa2","source":{"kind":"arxiv","id":"2007.08801","version":3},"attestation_state":"computed","paper":{"title":"Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hang Wang, Minghao Xu, Wenjun Zhang","submitted_at":"2020-07-17T07:52:44Z","abstract_excerpt":"Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation. Furthermore, the increase of modalities brings more difficulty in aligning feature distributions among multiple domains. To mitigate these problems, we propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework via exploring interactions among domains. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjac"},"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":"2007.08801","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-17T07:52:44Z","cross_cats_sorted":[],"title_canon_sha256":"381af23c64e39cbfc93c1c3730b69a4d2e0b81eeb280494811998849bb085e7b","abstract_canon_sha256":"1f6241cad92528cb0d5d488fed14e840cc2e7b823c7e98fe2fcbc556034ebe59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:51.188820Z","signature_b64":"bpHMKmbcdpwgZ3e1Yx8Wg3pd9McxOGaH4ytm2Lmb7mFo9M5fiX+VuTvUmK30EIIkHn/73fJKR88vaRZSnIqkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"215d9fa5818ec1c7d369f0bc3f43b470bf0968b5fa27deee922b927553dd6fa2","last_reissued_at":"2026-07-05T01:22:51.188385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:51.188385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hang Wang, Minghao Xu, Wenjun Zhang","submitted_at":"2020-07-17T07:52:44Z","abstract_excerpt":"Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation. Furthermore, the increase of modalities brings more difficulty in aligning feature distributions among multiple domains. To mitigate these problems, we propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework via exploring interactions among domains. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08801","kind":"arxiv","version":3},"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/2007.08801/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":"2007.08801","created_at":"2026-07-05T01:22:51.188446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08801v3","created_at":"2026-07-05T01:22:51.188446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08801","created_at":"2026-07-05T01:22:51.188446+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFOZ7JMBR3A4","created_at":"2026-07-05T01:22:51.188446+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFOZ7JMBR3A4PU3J","created_at":"2026-07-05T01:22:51.188446+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFOZ7JMB","created_at":"2026-07-05T01:22:51.188446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20380","citing_title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC","json":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC.json","graph_json":"https://pith.science/api/pith-number/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/graph.json","events_json":"https://pith.science/api/pith-number/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/events.json","paper":"https://pith.science/paper/EFOZ7JMB"},"agent_actions":{"view_html":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC","download_json":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC.json","view_paper":"https://pith.science/paper/EFOZ7JMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08801&json=true","fetch_graph":"https://pith.science/api/pith-number/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/graph.json","fetch_events":"https://pith.science/api/pith-number/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/action/storage_attestation","attest_author":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/action/author_attestation","sign_citation":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/action/citation_signature","submit_replication":"https://pith.science/pith/EFOZ7JMBR3A4PU3J6C6D6Q5UOC/action/replication_record"}},"created_at":"2026-07-05T01:22:51.188446+00:00","updated_at":"2026-07-05T01:22:51.188446+00:00"}