{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RLLJCFG7YR6R3A6RSNXUHQDIKR","short_pith_number":"pith:RLLJCFG7","schema_version":"1.0","canonical_sha256":"8ad69114dfc47d1d83d1936f43c0685455a6d900fdd31711592d33c5b95e5fa8","source":{"kind":"arxiv","id":"2510.00458","version":3},"attestation_state":"computed","paper":{"title":"VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atif Belal, Eric Granger, Heitor R. Medeiros, Marco Pedersoli","submitted_at":"2025-10-01T03:17:56Z","abstract_excerpt":"Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt models online using only unlabeled target data. However, despite substantial progress in TTA for vision-language classification, TTA for VLODs remains largely unexplored. The only prior method relies on a mean-teacher framework that introduces significant latency and memory overhead. To this end, we introduce \\textsc{VLOD-TTA}, a TTA method that leverages dense "},"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":"2510.00458","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T03:17:56Z","cross_cats_sorted":[],"title_canon_sha256":"77e38a1ad3da3d42ee3e0dcdea033a8e2df8d234aaa57a6604dd21b4af43d3ad","abstract_canon_sha256":"8a0f2165ad3384088399b472dce58ee56fe4d4122fdcd393ffdef24c9ec9311c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:27.141671Z","signature_b64":"xO0yVEj7BhLCuRtd5aJecl8g2ae9wY8q1XdRJtfwHfzwwJUxwGs/1GrCH34C6S4ViFdr0CN0L6PQb6vNOtO+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad69114dfc47d1d83d1936f43c0685455a6d900fdd31711592d33c5b95e5fa8","last_reissued_at":"2026-06-30T01:17:27.140939Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:27.140939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atif Belal, Eric Granger, Heitor R. Medeiros, Marco Pedersoli","submitted_at":"2025-10-01T03:17:56Z","abstract_excerpt":"Vision-language object detectors (VLODs) such as YOLO-World and Grounding DINO exhibit strong zero-shot generalization, but their performance degrades under distribution shift. Test-time adaptation (TTA) offers a practical way to adapt models online using only unlabeled target data. However, despite substantial progress in TTA for vision-language classification, TTA for VLODs remains largely unexplored. The only prior method relies on a mean-teacher framework that introduces significant latency and memory overhead. To this end, we introduce \\textsc{VLOD-TTA}, a TTA method that leverages dense "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00458","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/2510.00458/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":"2510.00458","created_at":"2026-06-30T01:17:27.141036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.00458v3","created_at":"2026-06-30T01:17:27.141036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00458","created_at":"2026-06-30T01:17:27.141036+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLLJCFG7YR6R","created_at":"2026-06-30T01:17:27.141036+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLLJCFG7YR6R3A6R","created_at":"2026-06-30T01:17:27.141036+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLLJCFG7","created_at":"2026-06-30T01:17:27.141036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.04531","citing_title":"Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR","json":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR.json","graph_json":"https://pith.science/api/pith-number/RLLJCFG7YR6R3A6RSNXUHQDIKR/graph.json","events_json":"https://pith.science/api/pith-number/RLLJCFG7YR6R3A6RSNXUHQDIKR/events.json","paper":"https://pith.science/paper/RLLJCFG7"},"agent_actions":{"view_html":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR","download_json":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR.json","view_paper":"https://pith.science/paper/RLLJCFG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.00458&json=true","fetch_graph":"https://pith.science/api/pith-number/RLLJCFG7YR6R3A6RSNXUHQDIKR/graph.json","fetch_events":"https://pith.science/api/pith-number/RLLJCFG7YR6R3A6RSNXUHQDIKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR/action/storage_attestation","attest_author":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR/action/author_attestation","sign_citation":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR/action/citation_signature","submit_replication":"https://pith.science/pith/RLLJCFG7YR6R3A6RSNXUHQDIKR/action/replication_record"}},"created_at":"2026-06-30T01:17:27.141036+00:00","updated_at":"2026-06-30T01:17:27.141036+00:00"}