{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YS3GDW3ATQJ3MFATMMTHJIXMNI","short_pith_number":"pith:YS3GDW3A","schema_version":"1.0","canonical_sha256":"c4b661db609c13b61413632674a2ec6a064ee6fad72afc8501662afeee51d7a5","source":{"kind":"arxiv","id":"2501.00818","version":1},"attestation_state":"computed","paper":{"title":"SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Huiyu Zhou, Jiamei Liu, Ningzhong Liu, Xinru Meng","submitted_at":"2025-01-01T12:19:17Z","abstract_excerpt":"Test-time Adaptation (TTA) aims to improve model performance when the model encounters domain changes after deployment. The standard TTA mainly considers the case where the target domain is static, while the continual TTA needs to undergo a sequence of domain changes. This encounters a significant challenge as the model needs to adapt for the long-term and is unaware of when the domain changes occur. The quality of pseudo-labels is hard to guarantee. Noisy pseudo-labels produced by simple self-training methods can cause error accumulation and catastrophic forgetting. In this work, we propose a"},"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":"2501.00818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-01T12:19:17Z","cross_cats_sorted":[],"title_canon_sha256":"152734962f199e68514e5dbb42003b614e72a434a7d3a4a36ad30aa18b1ed6d9","abstract_canon_sha256":"9987cbb603c15df403771d4a47da6e10f14d1cf58d18a70727017416d83d4e47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:10.726098Z","signature_b64":"VptLFN67Zd1oCgucRHI0RwiJP63VNmebknhawHYBqFvcCqutQCgf/MQ4VAo0yhVw9FCLnQb0KgEPw/uT/NxOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4b661db609c13b61413632674a2ec6a064ee6fad72afc8501662afeee51d7a5","last_reissued_at":"2026-07-05T09:56:10.725707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:10.725707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Huiyu Zhou, Jiamei Liu, Ningzhong Liu, Xinru Meng","submitted_at":"2025-01-01T12:19:17Z","abstract_excerpt":"Test-time Adaptation (TTA) aims to improve model performance when the model encounters domain changes after deployment. The standard TTA mainly considers the case where the target domain is static, while the continual TTA needs to undergo a sequence of domain changes. This encounters a significant challenge as the model needs to adapt for the long-term and is unaware of when the domain changes occur. The quality of pseudo-labels is hard to guarantee. Noisy pseudo-labels produced by simple self-training methods can cause error accumulation and catastrophic forgetting. In this work, we propose a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00818","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/2501.00818/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":"2501.00818","created_at":"2026-07-05T09:56:10.725774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00818v1","created_at":"2026-07-05T09:56:10.725774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00818","created_at":"2026-07-05T09:56:10.725774+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS3GDW3ATQJ3","created_at":"2026-07-05T09:56:10.725774+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS3GDW3ATQJ3MFAT","created_at":"2026-07-05T09:56:10.725774+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS3GDW3A","created_at":"2026-07-05T09:56:10.725774+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/YS3GDW3ATQJ3MFATMMTHJIXMNI","json":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI.json","graph_json":"https://pith.science/api/pith-number/YS3GDW3ATQJ3MFATMMTHJIXMNI/graph.json","events_json":"https://pith.science/api/pith-number/YS3GDW3ATQJ3MFATMMTHJIXMNI/events.json","paper":"https://pith.science/paper/YS3GDW3A"},"agent_actions":{"view_html":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI","download_json":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI.json","view_paper":"https://pith.science/paper/YS3GDW3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00818&json=true","fetch_graph":"https://pith.science/api/pith-number/YS3GDW3ATQJ3MFATMMTHJIXMNI/graph.json","fetch_events":"https://pith.science/api/pith-number/YS3GDW3ATQJ3MFATMMTHJIXMNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI/action/storage_attestation","attest_author":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI/action/author_attestation","sign_citation":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI/action/citation_signature","submit_replication":"https://pith.science/pith/YS3GDW3ATQJ3MFATMMTHJIXMNI/action/replication_record"}},"created_at":"2026-07-05T09:56:10.725774+00:00","updated_at":"2026-07-05T09:56:10.725774+00:00"}