{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QBGSA4HQKE4YRZASJHDGSTSM4G","short_pith_number":"pith:QBGSA4HQ","schema_version":"1.0","canonical_sha256":"804d2070f0513988e41249c6694e4ce1b6a53624c76766e7b2e5661da45c00c0","source":{"kind":"arxiv","id":"2506.21042","version":2},"attestation_state":"computed","paper":{"title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyong He, Liaoni Wu, Yuxiang Ji, Zhuoyue Tan","submitted_at":"2025-06-26T06:42:23Z","abstract_excerpt":"Detectors often suffer from performance drop due to domain gap between training and testing data. Recent methods explore diffusion models applied to domain generalization (DG) and adaptation (DA) tasks, but still struggle with large inference costs and have not yet fully leveraged the capabilities of diffusion models. We propose to tackle these problems by extracting intermediate features from a single-step diffusion process, improving feature collection and fusion to reduce inference time by 75% while enhancing performance on source domains (i.e., Fitness). Then, we construct an object-center"},"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":"2506.21042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T06:42:23Z","cross_cats_sorted":[],"title_canon_sha256":"48eb2c3e76a8b7e9b60b733c648810272139b6d06b9f3a3c48c75f8f4e0d84a9","abstract_canon_sha256":"2a88c061678ae14d99653fdb626797537f96eee5a1beb41bf184757682e74f74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:38.366106Z","signature_b64":"YRSGYeNdJ2nfXKnf8GL739rtnXuHDPKV2WuKuWLU0Bkj4rO8fvXWSmwhHtJYi/IdXCUd/6ycIM0GuyLQACqHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"804d2070f0513988e41249c6694e4ce1b6a53624c76766e7b2e5661da45c00c0","last_reissued_at":"2026-07-05T11:28:38.365568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:38.365568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyong He, Liaoni Wu, Yuxiang Ji, Zhuoyue Tan","submitted_at":"2025-06-26T06:42:23Z","abstract_excerpt":"Detectors often suffer from performance drop due to domain gap between training and testing data. Recent methods explore diffusion models applied to domain generalization (DG) and adaptation (DA) tasks, but still struggle with large inference costs and have not yet fully leveraged the capabilities of diffusion models. We propose to tackle these problems by extracting intermediate features from a single-step diffusion process, improving feature collection and fusion to reduce inference time by 75% while enhancing performance on source domains (i.e., Fitness). Then, we construct an object-center"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21042","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/2506.21042/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":"2506.21042","created_at":"2026-07-05T11:28:38.365629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21042v2","created_at":"2026-07-05T11:28:38.365629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21042","created_at":"2026-07-05T11:28:38.365629+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBGSA4HQKE4Y","created_at":"2026-07-05T11:28:38.365629+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBGSA4HQKE4YRZAS","created_at":"2026-07-05T11:28:38.365629+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBGSA4HQ","created_at":"2026-07-05T11:28:38.365629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03835","citing_title":"Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G","json":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G.json","graph_json":"https://pith.science/api/pith-number/QBGSA4HQKE4YRZASJHDGSTSM4G/graph.json","events_json":"https://pith.science/api/pith-number/QBGSA4HQKE4YRZASJHDGSTSM4G/events.json","paper":"https://pith.science/paper/QBGSA4HQ"},"agent_actions":{"view_html":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G","download_json":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G.json","view_paper":"https://pith.science/paper/QBGSA4HQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21042&json=true","fetch_graph":"https://pith.science/api/pith-number/QBGSA4HQKE4YRZASJHDGSTSM4G/graph.json","fetch_events":"https://pith.science/api/pith-number/QBGSA4HQKE4YRZASJHDGSTSM4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G/action/storage_attestation","attest_author":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G/action/author_attestation","sign_citation":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G/action/citation_signature","submit_replication":"https://pith.science/pith/QBGSA4HQKE4YRZASJHDGSTSM4G/action/replication_record"}},"created_at":"2026-07-05T11:28:38.365629+00:00","updated_at":"2026-07-05T11:28:38.365629+00:00"}