{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JSNY3WJF72PDUPENFRGTD757SK","short_pith_number":"pith:JSNY3WJF","schema_version":"1.0","canonical_sha256":"4c9b8dd925fe9e3a3c8d2c4d31ffbf92b96b0ad0a4a8e8782637fc8a687af78b","source":{"kind":"arxiv","id":"2506.19022","version":1},"attestation_state":"computed","paper":{"title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhao, Jinlong Li, Lin Ma, Nicu Sebe, Qi Zang, Zequn Jie","submitted_at":"2025-06-23T18:17:39Z","abstract_excerpt":"Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios with changing target distributions. Existing CTTA methods primarily focus on mitigating the challenges of catastrophic forgetting and error accumulation. Though there have been emerging methods based on forgetting adaptation with parameter-efficient fine-tuning, they still struggle to balance competitive performance and efficient model adaptation, particularly in complex tasks like semantic segmentation. In this paper, to tackle the above issues, we propose a novel pip"},"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":"2506.19022","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T18:17:39Z","cross_cats_sorted":[],"title_canon_sha256":"2fe6dbb9da60cc458431a4d909a965231b6a25e606717e044f4eda74c6608619","abstract_canon_sha256":"587d74b0bb0fb4f146d791a1b0c309c1f02eecdead7dd1c26520218f55e02c5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:08.074471Z","signature_b64":"Re4axZkgCqYi1a1B6/xb0kDSMQT50bPki4hNhNkzrlhF3VcfFhqs1imTgL2leNbQFjskNPZ4lmmWys+ZC5SPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c9b8dd925fe9e3a3c8d2c4d31ffbf92b96b0ad0a4a8e8782637fc8a687af78b","last_reissued_at":"2026-07-05T11:26:08.073881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:08.073881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhao, Jinlong Li, Lin Ma, Nicu Sebe, Qi Zang, Zequn Jie","submitted_at":"2025-06-23T18:17:39Z","abstract_excerpt":"Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios with changing target distributions. Existing CTTA methods primarily focus on mitigating the challenges of catastrophic forgetting and error accumulation. Though there have been emerging methods based on forgetting adaptation with parameter-efficient fine-tuning, they still struggle to balance competitive performance and efficient model adaptation, particularly in complex tasks like semantic segmentation. In this paper, to tackle the above issues, we propose a novel pip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19022","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/2506.19022/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":"2506.19022","created_at":"2026-07-05T11:26:08.073944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19022v1","created_at":"2026-07-05T11:26:08.073944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19022","created_at":"2026-07-05T11:26:08.073944+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSNY3WJF72PD","created_at":"2026-07-05T11:26:08.073944+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSNY3WJF72PDUPEN","created_at":"2026-07-05T11:26:08.073944+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSNY3WJF","created_at":"2026-07-05T11:26:08.073944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01400","citing_title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK","json":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK.json","graph_json":"https://pith.science/api/pith-number/JSNY3WJF72PDUPENFRGTD757SK/graph.json","events_json":"https://pith.science/api/pith-number/JSNY3WJF72PDUPENFRGTD757SK/events.json","paper":"https://pith.science/paper/JSNY3WJF"},"agent_actions":{"view_html":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK","download_json":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK.json","view_paper":"https://pith.science/paper/JSNY3WJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19022&json=true","fetch_graph":"https://pith.science/api/pith-number/JSNY3WJF72PDUPENFRGTD757SK/graph.json","fetch_events":"https://pith.science/api/pith-number/JSNY3WJF72PDUPENFRGTD757SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK/action/storage_attestation","attest_author":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK/action/author_attestation","sign_citation":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK/action/citation_signature","submit_replication":"https://pith.science/pith/JSNY3WJF72PDUPENFRGTD757SK/action/replication_record"}},"created_at":"2026-07-05T11:26:08.073944+00:00","updated_at":"2026-07-05T11:26:08.073944+00:00"}