{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5UT27GPHP3OFIKPJTKX3HXGR6C","short_pith_number":"pith:5UT27GPH","schema_version":"1.0","canonical_sha256":"ed27af99e77edc5429e99aafb3dcd1f0ad948c6c1692d056a7e8995217b2d53e","source":{"kind":"arxiv","id":"2506.24063","version":1},"attestation_state":"computed","paper":{"title":"Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Deng Li, Yahong Han, Yang Li, Yaowei Wang","submitted_at":"2025-06-30T17:14:12Z","abstract_excerpt":"In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore"},"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":"2506.24063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T17:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"cf87b33a88857419507b550afd72d0b7298357d6bc7f203df61c4a6b60a51b6b","abstract_canon_sha256":"4ce7f1bdce8e229b465a4f94e9e486b3a8f1ce1c0e7e6129313d73382784e06f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:32.622600Z","signature_b64":"JYeTSJ5oB6ewLLLUbA7fYrynGBVSUKWGDOxgAIizmQWlmhGiG1go11CkUqQWKN6/XCvMD6I7SUGm1YJYno51Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed27af99e77edc5429e99aafb3dcd1f0ad948c6c1692d056a7e8995217b2d53e","last_reissued_at":"2026-07-05T11:29:32.621892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:32.621892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aming Wu, Deng Li, Yahong Han, Yang Li, Yaowei Wang","submitted_at":"2025-06-30T17:14:12Z","abstract_excerpt":"In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24063","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/2506.24063/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":"2506.24063","created_at":"2026-07-05T11:29:32.621987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.24063v1","created_at":"2026-07-05T11:29:32.621987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24063","created_at":"2026-07-05T11:29:32.621987+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UT27GPHP3OF","created_at":"2026-07-05T11:29:32.621987+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UT27GPHP3OFIKPJ","created_at":"2026-07-05T11:29:32.621987+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UT27GPH","created_at":"2026-07-05T11:29:32.621987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18608","citing_title":"Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C","json":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C.json","graph_json":"https://pith.science/api/pith-number/5UT27GPHP3OFIKPJTKX3HXGR6C/graph.json","events_json":"https://pith.science/api/pith-number/5UT27GPHP3OFIKPJTKX3HXGR6C/events.json","paper":"https://pith.science/paper/5UT27GPH"},"agent_actions":{"view_html":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C","download_json":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C.json","view_paper":"https://pith.science/paper/5UT27GPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.24063&json=true","fetch_graph":"https://pith.science/api/pith-number/5UT27GPHP3OFIKPJTKX3HXGR6C/graph.json","fetch_events":"https://pith.science/api/pith-number/5UT27GPHP3OFIKPJTKX3HXGR6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C/action/storage_attestation","attest_author":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C/action/author_attestation","sign_citation":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C/action/citation_signature","submit_replication":"https://pith.science/pith/5UT27GPHP3OFIKPJTKX3HXGR6C/action/replication_record"}},"created_at":"2026-07-05T11:29:32.621987+00:00","updated_at":"2026-07-05T11:29:32.621987+00:00"}