{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SBKGZS3A4FMDJEA4HS4LDCMK5V","short_pith_number":"pith:SBKGZS3A","schema_version":"1.0","canonical_sha256":"90546ccb60e15834901c3cb8b1898aed59550f33907d2b68c0e1af94fb7aca20","source":{"kind":"arxiv","id":"2403.10650","version":4},"attestation_state":"computed","paper":{"title":"PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoming Zhang, Sarthak Kumar Maharana, Yunhui Guo","submitted_at":"2024-03-15T19:35:10Z","abstract_excerpt":"Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains. A highly effective CTTA method involves applying layer-wise adaptive learning rates for selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. This work aims to overcome these limitations by identifying layers "},"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":"2403.10650","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T19:35:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"347c4eb8adb42d7cc3c5c4dd51af780317f6a0b89c2ab3ac23cdbdba79eeb9e4","abstract_canon_sha256":"c46eddcbea862b28d3fe2e84e541d36f2d98a2aecca056c70cfff07d4b6f8d92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:09.610684Z","signature_b64":"1gPeeM3rJ41zSHdvYaWmG79JmdsnJkpQG+SSTB23XOOXdTncbSjQfh9H+Du3Kl7fEKtGkV4C1qVVdu5HqpWZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90546ccb60e15834901c3cb8b1898aed59550f33907d2b68c0e1af94fb7aca20","last_reissued_at":"2026-07-05T10:05:09.610253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:09.610253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoming Zhang, Sarthak Kumar Maharana, Yunhui Guo","submitted_at":"2024-03-15T19:35:10Z","abstract_excerpt":"Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains. A highly effective CTTA method involves applying layer-wise adaptive learning rates for selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. This work aims to overcome these limitations by identifying layers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10650","kind":"arxiv","version":4},"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/2403.10650/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":"2403.10650","created_at":"2026-07-05T10:05:09.610309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10650v4","created_at":"2026-07-05T10:05:09.610309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10650","created_at":"2026-07-05T10:05:09.610309+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBKGZS3A4FMD","created_at":"2026-07-05T10:05:09.610309+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBKGZS3A4FMDJEA4","created_at":"2026-07-05T10:05:09.610309+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBKGZS3A","created_at":"2026-07-05T10:05:09.610309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20516","citing_title":"DCFS: Continual Test-Time Adaptation via Dual Consistency of Feature and Sample","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V","json":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V.json","graph_json":"https://pith.science/api/pith-number/SBKGZS3A4FMDJEA4HS4LDCMK5V/graph.json","events_json":"https://pith.science/api/pith-number/SBKGZS3A4FMDJEA4HS4LDCMK5V/events.json","paper":"https://pith.science/paper/SBKGZS3A"},"agent_actions":{"view_html":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V","download_json":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V.json","view_paper":"https://pith.science/paper/SBKGZS3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10650&json=true","fetch_graph":"https://pith.science/api/pith-number/SBKGZS3A4FMDJEA4HS4LDCMK5V/graph.json","fetch_events":"https://pith.science/api/pith-number/SBKGZS3A4FMDJEA4HS4LDCMK5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V/action/storage_attestation","attest_author":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V/action/author_attestation","sign_citation":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V/action/citation_signature","submit_replication":"https://pith.science/pith/SBKGZS3A4FMDJEA4HS4LDCMK5V/action/replication_record"}},"created_at":"2026-07-05T10:05:09.610309+00:00","updated_at":"2026-07-05T10:05:09.610309+00:00"}