{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y7DNJKP7SJ4KUA3FMUWH5ICSDA","short_pith_number":"pith:Y7DNJKP7","schema_version":"1.0","canonical_sha256":"c7c6d4a9ff9278aa0365652c7ea05218343832610c29c6b8b1cecb5df66c7875","source":{"kind":"arxiv","id":"2108.10860","version":1},"attestation_state":"computed","paper":{"title":"Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kate Saenko, Kuniaki Saito, Piotr Teterwak, Stan Sclaroff, Trevor Darrell","submitted_at":"2021-08-24T17:41:45Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled target data, which raises the question: How can we validate unsupervised adaptation techniques in a realistic way? We first empirically analyze existing criteria and demonstrate that they are not very effective for tuning hyper-parameters. Intuitively, a well-trained source classifier should embed tar"},"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":"2108.10860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-24T17:41:45Z","cross_cats_sorted":[],"title_canon_sha256":"f6d172e189258e76f602e65c4cab9235f4322b9c903d159d70ba04f37bbc9eb4","abstract_canon_sha256":"fbee9cdbdd2c5645e6c3802f115a2f275024d2d78a3db928ed5491b9d224d952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:40.657550Z","signature_b64":"SV52bo9iUVpAtV3+VW4FJx8OjPcGwCdmiPzpp2C+9rF5lJM98RrZDXMjPyG4/O0fAFpdXhg0uN3gGhOrDhdGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c6d4a9ff9278aa0365652c7ea05218343832610c29c6b8b1cecb5df66c7875","last_reissued_at":"2026-07-05T03:08:40.656847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:40.656847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kate Saenko, Kuniaki Saito, Piotr Teterwak, Stan Sclaroff, Trevor Darrell","submitted_at":"2021-08-24T17:41:45Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled target data, which raises the question: How can we validate unsupervised adaptation techniques in a realistic way? We first empirically analyze existing criteria and demonstrate that they are not very effective for tuning hyper-parameters. Intuitively, a well-trained source classifier should embed tar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10860","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/2108.10860/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":"2108.10860","created_at":"2026-07-05T03:08:40.656933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10860v1","created_at":"2026-07-05T03:08:40.656933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10860","created_at":"2026-07-05T03:08:40.656933+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7DNJKP7SJ4K","created_at":"2026-07-05T03:08:40.656933+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7DNJKP7SJ4KUA3F","created_at":"2026-07-05T03:08:40.656933+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7DNJKP7","created_at":"2026-07-05T03:08:40.656933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.00450","citing_title":"Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA","json":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA.json","graph_json":"https://pith.science/api/pith-number/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/graph.json","events_json":"https://pith.science/api/pith-number/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/events.json","paper":"https://pith.science/paper/Y7DNJKP7"},"agent_actions":{"view_html":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA","download_json":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA.json","view_paper":"https://pith.science/paper/Y7DNJKP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10860&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/action/storage_attestation","attest_author":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/action/author_attestation","sign_citation":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/action/citation_signature","submit_replication":"https://pith.science/pith/Y7DNJKP7SJ4KUA3FMUWH5ICSDA/action/replication_record"}},"created_at":"2026-07-05T03:08:40.656933+00:00","updated_at":"2026-07-05T03:08:40.656933+00:00"}