{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCH6GTNW55NJPDHRPSN7HLQ4X2","short_pith_number":"pith:GCH6GTNW","schema_version":"1.0","canonical_sha256":"308fe34db6ef5a978cf17c9bf3ae1cbe9b7561e80a7107378eac4cdb2440f2a2","source":{"kind":"arxiv","id":"2508.19613","version":1},"attestation_state":"computed","paper":{"title":"ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenzhi Liu, Mahsa Baktashmotlagh, Ruihong Qiu, Yanran Tang, Zi Huang","submitted_at":"2025-08-27T06:46:15Z","abstract_excerpt":"Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance. Existing methods often rely on predicted class probabilities (softmax scores) or data similarity metrics. While softmax-based approaches benefit from representing predictions on the standard simplex, compressing logits into probabilities leads to information loss. Meanwhile, similarity-based methods can be computationally expensive and domain-specific, limiting their broader applicability. In this paper, we introduce"},"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":"2508.19613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T06:46:15Z","cross_cats_sorted":[],"title_canon_sha256":"106edb39d472c628f721d897e1bfb9ce4c36f583e7896bd33e940f7e0401e6f7","abstract_canon_sha256":"25b438bd5e8807adfefdc93738c5f23cdf258f61019102ccad1b8a0b8eec1734"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:15.060223Z","signature_b64":"9X79EDcwJSZZ+XQ0rr3S3pzbvKurMUfiLFUfR6wAhBNXPRB1DtHDvQhOrd95XYGNEiHD92a52vkIL4T2qQwFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"308fe34db6ef5a978cf17c9bf3ae1cbe9b7561e80a7107378eac4cdb2440f2a2","last_reissued_at":"2026-07-05T12:00:15.059734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:15.059734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenzhi Liu, Mahsa Baktashmotlagh, Ruihong Qiu, Yanran Tang, Zi Huang","submitted_at":"2025-08-27T06:46:15Z","abstract_excerpt":"Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance. Existing methods often rely on predicted class probabilities (softmax scores) or data similarity metrics. While softmax-based approaches benefit from representing predictions on the standard simplex, compressing logits into probabilities leads to information loss. Meanwhile, similarity-based methods can be computationally expensive and domain-specific, limiting their broader applicability. In this paper, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19613","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/2508.19613/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":"2508.19613","created_at":"2026-07-05T12:00:15.059793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19613v1","created_at":"2026-07-05T12:00:15.059793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19613","created_at":"2026-07-05T12:00:15.059793+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCH6GTNW55NJ","created_at":"2026-07-05T12:00:15.059793+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCH6GTNW55NJPDHR","created_at":"2026-07-05T12:00:15.059793+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCH6GTNW","created_at":"2026-07-05T12:00:15.059793+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/GCH6GTNW55NJPDHRPSN7HLQ4X2","json":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2.json","graph_json":"https://pith.science/api/pith-number/GCH6GTNW55NJPDHRPSN7HLQ4X2/graph.json","events_json":"https://pith.science/api/pith-number/GCH6GTNW55NJPDHRPSN7HLQ4X2/events.json","paper":"https://pith.science/paper/GCH6GTNW"},"agent_actions":{"view_html":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2","download_json":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2.json","view_paper":"https://pith.science/paper/GCH6GTNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19613&json=true","fetch_graph":"https://pith.science/api/pith-number/GCH6GTNW55NJPDHRPSN7HLQ4X2/graph.json","fetch_events":"https://pith.science/api/pith-number/GCH6GTNW55NJPDHRPSN7HLQ4X2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2/action/storage_attestation","attest_author":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2/action/author_attestation","sign_citation":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2/action/citation_signature","submit_replication":"https://pith.science/pith/GCH6GTNW55NJPDHRPSN7HLQ4X2/action/replication_record"}},"created_at":"2026-07-05T12:00:15.059793+00:00","updated_at":"2026-07-05T12:00:15.059793+00:00"}