{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AJU2RWUZD6HEY6EXBUS6EJRBDY","short_pith_number":"pith:AJU2RWUZ","schema_version":"1.0","canonical_sha256":"0269a8da991f8e4c78970d25e226211e02708dbd563e917901f8dca43968d2be","source":{"kind":"arxiv","id":"2304.10113","version":1},"attestation_state":"computed","paper":{"title":"SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Goirik Chakrabarty, Manogna Sreenivas, Soma Biswas","submitted_at":"2023-04-20T06:38:33Z","abstract_excerpt":"Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the following characteristics required for online adaptation: 1) can work seamlessly with different (preferably small) batch sizes to reduce latency; 2) should continue to work well for the source domain; 3) should have minimal tunable hyper-parameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed SATA framework modifies the batch-n"},"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":"2304.10113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T06:38:33Z","cross_cats_sorted":[],"title_canon_sha256":"9abeccf4eacd32cfa31daced5e1a53dd6e76653d3cf6b95251acdf36ae68ab13","abstract_canon_sha256":"82e3de8e3777a93e74bfdc74f34b094c8419a6c32a162639ede9be940430f2dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:54.142634Z","signature_b64":"whQH7DB61nbxOMHG+lVz8QWe4MSed8k3l61FkGlwQ66IgxsPHbKYFVhy8fNuws4SoDublchd37I/uOsNrHm7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0269a8da991f8e4c78970d25e226211e02708dbd563e917901f8dca43968d2be","last_reissued_at":"2026-07-05T06:02:54.142191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:54.142191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Goirik Chakrabarty, Manogna Sreenivas, Soma Biswas","submitted_at":"2023-04-20T06:38:33Z","abstract_excerpt":"Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the following characteristics required for online adaptation: 1) can work seamlessly with different (preferably small) batch sizes to reduce latency; 2) should continue to work well for the source domain; 3) should have minimal tunable hyper-parameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed SATA framework modifies the batch-n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10113","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/2304.10113/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":"2304.10113","created_at":"2026-07-05T06:02:54.142255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10113v1","created_at":"2026-07-05T06:02:54.142255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10113","created_at":"2026-07-05T06:02:54.142255+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJU2RWUZD6HE","created_at":"2026-07-05T06:02:54.142255+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJU2RWUZD6HEY6EX","created_at":"2026-07-05T06:02:54.142255+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJU2RWUZ","created_at":"2026-07-05T06:02:54.142255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02998","citing_title":"Conformal Uncertainty Indicator for Continual Test-Time Adaptation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY","json":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY.json","graph_json":"https://pith.science/api/pith-number/AJU2RWUZD6HEY6EXBUS6EJRBDY/graph.json","events_json":"https://pith.science/api/pith-number/AJU2RWUZD6HEY6EXBUS6EJRBDY/events.json","paper":"https://pith.science/paper/AJU2RWUZ"},"agent_actions":{"view_html":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY","download_json":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY.json","view_paper":"https://pith.science/paper/AJU2RWUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10113&json=true","fetch_graph":"https://pith.science/api/pith-number/AJU2RWUZD6HEY6EXBUS6EJRBDY/graph.json","fetch_events":"https://pith.science/api/pith-number/AJU2RWUZD6HEY6EXBUS6EJRBDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY/action/storage_attestation","attest_author":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY/action/author_attestation","sign_citation":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY/action/citation_signature","submit_replication":"https://pith.science/pith/AJU2RWUZD6HEY6EXBUS6EJRBDY/action/replication_record"}},"created_at":"2026-07-05T06:02:54.142255+00:00","updated_at":"2026-07-05T06:02:54.142255+00:00"}