{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QUJCZDALJODACMMB3OFWT4NORM","short_pith_number":"pith:QUJCZDAL","schema_version":"1.0","canonical_sha256":"85122c8c0b4b86013181db8b69f1ae8b370e9eaeffe87a74be0d12acac71c0e0","source":{"kind":"arxiv","id":"2602.18528","version":2},"attestation_state":"computed","paper":{"title":"Audio-Visual Continual Test-Time Adaptation without Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Akshay Mehra, Bhavya Ramakrishna, Guan-Ming Su, Sarthak Kumar Maharana, Yunhui Guo","submitted_at":"2026-02-20T04:55:01Z","abstract_excerpt":"Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online cross-modal learning and eventually leads to poor accuracy. While previous works have tackled this problem, we find that SOTA methods suffer from catastrophic forgetting where the model's performance drops well below even the source model due to continual parameter updates at test-time. In this work, we first show that adapting only the modality fusion layer "},"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":"2602.18528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T04:55:01Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"81913402a2fb0acc11d40c64130bd71c7861fc7fd314434c550d91d9c18c7ff0","abstract_canon_sha256":"b6c0ef1c3e321286d2f0bba83299827e3ed46838c19c3a18769c8084f6fdec79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:34.494071Z","signature_b64":"buur1D5LxpjkzLWjgaOpYhjlzlNwk/M4lthkdRZstqXNRiXPE2PLCER7tpi9eY9zIvAdebFE5fLAUcXFUllSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85122c8c0b4b86013181db8b69f1ae8b370e9eaeffe87a74be0d12acac71c0e0","last_reissued_at":"2026-06-30T01:17:34.493268Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:34.493268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Continual Test-Time Adaptation without Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Akshay Mehra, Bhavya Ramakrishna, Guan-Ming Su, Sarthak Kumar Maharana, Yunhui Guo","submitted_at":"2026-02-20T04:55:01Z","abstract_excerpt":"Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online cross-modal learning and eventually leads to poor accuracy. While previous works have tackled this problem, we find that SOTA methods suffer from catastrophic forgetting where the model's performance drops well below even the source model due to continual parameter updates at test-time. In this work, we first show that adapting only the modality fusion layer "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18528","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/2602.18528/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":"2602.18528","created_at":"2026-06-30T01:17:34.493370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18528v2","created_at":"2026-06-30T01:17:34.493370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18528","created_at":"2026-06-30T01:17:34.493370+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUJCZDALJODA","created_at":"2026-06-30T01:17:34.493370+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUJCZDALJODACMMB","created_at":"2026-06-30T01:17:34.493370+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUJCZDAL","created_at":"2026-06-30T01:17:34.493370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM","json":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM.json","graph_json":"https://pith.science/api/pith-number/QUJCZDALJODACMMB3OFWT4NORM/graph.json","events_json":"https://pith.science/api/pith-number/QUJCZDALJODACMMB3OFWT4NORM/events.json","paper":"https://pith.science/paper/QUJCZDAL"},"agent_actions":{"view_html":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM","download_json":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM.json","view_paper":"https://pith.science/paper/QUJCZDAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18528&json=true","fetch_graph":"https://pith.science/api/pith-number/QUJCZDALJODACMMB3OFWT4NORM/graph.json","fetch_events":"https://pith.science/api/pith-number/QUJCZDALJODACMMB3OFWT4NORM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM/action/storage_attestation","attest_author":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM/action/author_attestation","sign_citation":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM/action/citation_signature","submit_replication":"https://pith.science/pith/QUJCZDALJODACMMB3OFWT4NORM/action/replication_record"}},"created_at":"2026-06-30T01:17:34.493370+00:00","updated_at":"2026-06-30T01:17:34.493370+00:00"}