{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HXYVQLBB4E5I4OBU73RNZTK7EB","short_pith_number":"pith:HXYVQLBB","schema_version":"1.0","canonical_sha256":"3df1582c21e13a8e3834fee2dccd5f2062d6e58a303f98f41e6660cdbcc8f8d1","source":{"kind":"arxiv","id":"2109.09033","version":2},"attestation_state":"computed","paper":{"title":"Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Bo Zhang, Ruoyao Li, Tao Chen","submitted_at":"2021-09-19T00:27:08Z","abstract_excerpt":"Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. First, they mainly align marginal distribution by unsupervised cross-domain feature matching, and ignore each feature's categorical and positional information that can be exploited for conditional alignment; Second, they treat all classes as equally important for transferring cross-domain knowledg"},"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":"2109.09033","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-19T00:27:08Z","cross_cats_sorted":[],"title_canon_sha256":"0e6da641d85c9960b769bf9486498e81dc1739df52ccde3119589c0854bb3fa0","abstract_canon_sha256":"caeb61d404a1711bf6d884068c1f3d985cf7f27e118dee121edf739c2dd1d39f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:13.114051Z","signature_b64":"nUzLzRpFtC462FHQActliIFN31e5NbgMyPnGHNzT4gHT8NUB0cY6TH/6ZM59m7jMYjE3xa37CIpBkD6S0thHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3df1582c21e13a8e3834fee2dccd5f2062d6e58a303f98f41e6660cdbcc8f8d1","last_reissued_at":"2026-07-05T04:05:13.113712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:13.113712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Bo Zhang, Ruoyao Li, Tao Chen","submitted_at":"2021-09-19T00:27:08Z","abstract_excerpt":"Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. First, they mainly align marginal distribution by unsupervised cross-domain feature matching, and ignore each feature's categorical and positional information that can be exploited for conditional alignment; Second, they treat all classes as equally important for transferring cross-domain knowledg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09033","kind":"arxiv","version":2},"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/2109.09033/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":"2109.09033","created_at":"2026-07-05T04:05:13.113768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09033v2","created_at":"2026-07-05T04:05:13.113768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09033","created_at":"2026-07-05T04:05:13.113768+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXYVQLBB4E5I","created_at":"2026-07-05T04:05:13.113768+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXYVQLBB4E5I4OBU","created_at":"2026-07-05T04:05:13.113768+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXYVQLBB","created_at":"2026-07-05T04:05:13.113768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21516","citing_title":"ST-DAI: Single-shot 2.5D Spatial Transcriptomics with Intra-Sample Domain Adaptive Imputation for Cost-efficient 3D Reconstruction","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB","json":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB.json","graph_json":"https://pith.science/api/pith-number/HXYVQLBB4E5I4OBU73RNZTK7EB/graph.json","events_json":"https://pith.science/api/pith-number/HXYVQLBB4E5I4OBU73RNZTK7EB/events.json","paper":"https://pith.science/paper/HXYVQLBB"},"agent_actions":{"view_html":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB","download_json":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB.json","view_paper":"https://pith.science/paper/HXYVQLBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09033&json=true","fetch_graph":"https://pith.science/api/pith-number/HXYVQLBB4E5I4OBU73RNZTK7EB/graph.json","fetch_events":"https://pith.science/api/pith-number/HXYVQLBB4E5I4OBU73RNZTK7EB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB/action/storage_attestation","attest_author":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB/action/author_attestation","sign_citation":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB/action/citation_signature","submit_replication":"https://pith.science/pith/HXYVQLBB4E5I4OBU73RNZTK7EB/action/replication_record"}},"created_at":"2026-07-05T04:05:13.113768+00:00","updated_at":"2026-07-05T04:05:13.113768+00:00"}