{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VI6SIEOWL4BTYI5EVVHP5UTXSU","short_pith_number":"pith:VI6SIEOW","schema_version":"1.0","canonical_sha256":"aa3d2411d65f033c23a4ad4efed277951256f11c3addf989688961641929b4b2","source":{"kind":"arxiv","id":"2307.04033","version":3},"attestation_state":"computed","paper":{"title":"Probabilistic Test-Time Generalization by Variational Neighbor-Labeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cees G. M. Snoek, Jiayi Shen, Sameer Ambekar, Xiantong Zhen, Zehao Xiao","submitted_at":"2023-07-08T18:58:08Z","abstract_excerpt":"This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation of source training and target testing, but exploit the value of the unlabeled target data itself during inference. We make three contributions. First, we propose probabilistic pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. We formulate the generalization at test time as a variational inference problem, by modeling pseudo labels as distributions, to conside"},"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":"2307.04033","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-08T18:58:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d211fc5c01be51132f7c9a5c0992fe39ee5a85384d481afba1c08d3d9649394","abstract_canon_sha256":"822eede086c69aac9ec01525ddc511b93ca40f752c4c50e5c5708305edc00faa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:33.403385Z","signature_b64":"f+LEe3AJmxb3xYsXa7GgAKU/N8masBgtLq5m+aOehfdaeZCWMX9RX6SZeBFoWU0OSug9t236ek0WQLJVuR3ZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa3d2411d65f033c23a4ad4efed277951256f11c3addf989688961641929b4b2","last_reissued_at":"2026-07-05T08:38:33.402886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:33.402886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Test-Time Generalization by Variational Neighbor-Labeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cees G. M. Snoek, Jiayi Shen, Sameer Ambekar, Xiantong Zhen, Zehao Xiao","submitted_at":"2023-07-08T18:58:08Z","abstract_excerpt":"This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation of source training and target testing, but exploit the value of the unlabeled target data itself during inference. We make three contributions. First, we propose probabilistic pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. We formulate the generalization at test time as a variational inference problem, by modeling pseudo labels as distributions, to conside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04033","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/2307.04033/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":"2307.04033","created_at":"2026-07-05T08:38:33.402949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04033v3","created_at":"2026-07-05T08:38:33.402949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04033","created_at":"2026-07-05T08:38:33.402949+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI6SIEOWL4BT","created_at":"2026-07-05T08:38:33.402949+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI6SIEOWL4BTYI5E","created_at":"2026-07-05T08:38:33.402949+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI6SIEOW","created_at":"2026-07-05T08:38:33.402949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02287","citing_title":"SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU","json":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU.json","graph_json":"https://pith.science/api/pith-number/VI6SIEOWL4BTYI5EVVHP5UTXSU/graph.json","events_json":"https://pith.science/api/pith-number/VI6SIEOWL4BTYI5EVVHP5UTXSU/events.json","paper":"https://pith.science/paper/VI6SIEOW"},"agent_actions":{"view_html":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU","download_json":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU.json","view_paper":"https://pith.science/paper/VI6SIEOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04033&json=true","fetch_graph":"https://pith.science/api/pith-number/VI6SIEOWL4BTYI5EVVHP5UTXSU/graph.json","fetch_events":"https://pith.science/api/pith-number/VI6SIEOWL4BTYI5EVVHP5UTXSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU/action/storage_attestation","attest_author":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU/action/author_attestation","sign_citation":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU/action/citation_signature","submit_replication":"https://pith.science/pith/VI6SIEOWL4BTYI5EVVHP5UTXSU/action/replication_record"}},"created_at":"2026-07-05T08:38:33.402949+00:00","updated_at":"2026-07-05T08:38:33.402949+00:00"}