{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VMRX6RFNWNK7O2W6WEIGSRLYTR","short_pith_number":"pith:VMRX6RFN","schema_version":"1.0","canonical_sha256":"ab237f44adb355f76adeb1106945789c78313bf8071ee53cef2a9467c3f04250","source":{"kind":"arxiv","id":"2208.09198","version":3},"attestation_state":"computed","paper":{"title":"Test-time Training for Data-efficient UCDR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Samanta, Aheli Saha, Soma Biswas, Soumava Paul, Titir Dutta","submitted_at":"2022-08-19T07:50:04Z","abstract_excerpt":"Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction. A common practice in any such generalized classification or retrieval algorithm is to exploit samples from many domains during training to learn a domain-invariant representation of data. Such criterion is often restrictive, and thus in this work, for the first time, we explore the generalized retrieval problem in a data-efficient manner. Specifically, we aim to generalize any pre-trained cross-dom"},"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":"2208.09198","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T07:50:04Z","cross_cats_sorted":[],"title_canon_sha256":"b54c37f049bb807c3036ea2bd1bd2df1ae0551fa7933321a5ec710a74bb1d86a","abstract_canon_sha256":"8b87baeaec330b55994c9060f67449caf0775eb639c738fa77d90fe15e8f355b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:38.908061Z","signature_b64":"oATel1tbDsNfrajwdBgk3IRiqrA6HsUb7zwcsUFefRMh+7+DL9P+CytTuSpbnO0KEEZfvgNLhD1Hd3Fu2naHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab237f44adb355f76adeb1106945789c78313bf8071ee53cef2a9467c3f04250","last_reissued_at":"2026-07-05T05:59:38.907717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:38.907717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-time Training for Data-efficient UCDR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Samanta, Aheli Saha, Soma Biswas, Soumava Paul, Titir Dutta","submitted_at":"2022-08-19T07:50:04Z","abstract_excerpt":"Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction. A common practice in any such generalized classification or retrieval algorithm is to exploit samples from many domains during training to learn a domain-invariant representation of data. Such criterion is often restrictive, and thus in this work, for the first time, we explore the generalized retrieval problem in a data-efficient manner. Specifically, we aim to generalize any pre-trained cross-dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09198","kind":"arxiv","version":3},"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/2208.09198/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":"2208.09198","created_at":"2026-07-05T05:59:38.907773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09198v3","created_at":"2026-07-05T05:59:38.907773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09198","created_at":"2026-07-05T05:59:38.907773+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMRX6RFNWNK7","created_at":"2026-07-05T05:59:38.907773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMRX6RFNWNK7O2W6","created_at":"2026-07-05T05:59:38.907773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMRX6RFN","created_at":"2026-07-05T05:59:38.907773+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/VMRX6RFNWNK7O2W6WEIGSRLYTR","json":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR.json","graph_json":"https://pith.science/api/pith-number/VMRX6RFNWNK7O2W6WEIGSRLYTR/graph.json","events_json":"https://pith.science/api/pith-number/VMRX6RFNWNK7O2W6WEIGSRLYTR/events.json","paper":"https://pith.science/paper/VMRX6RFN"},"agent_actions":{"view_html":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR","download_json":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR.json","view_paper":"https://pith.science/paper/VMRX6RFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09198&json=true","fetch_graph":"https://pith.science/api/pith-number/VMRX6RFNWNK7O2W6WEIGSRLYTR/graph.json","fetch_events":"https://pith.science/api/pith-number/VMRX6RFNWNK7O2W6WEIGSRLYTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR/action/storage_attestation","attest_author":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR/action/author_attestation","sign_citation":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR/action/citation_signature","submit_replication":"https://pith.science/pith/VMRX6RFNWNK7O2W6WEIGSRLYTR/action/replication_record"}},"created_at":"2026-07-05T05:59:38.907773+00:00","updated_at":"2026-07-05T05:59:38.907773+00:00"}