{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IX5BJV4WAAGLAVLA4OHTUB45C2","short_pith_number":"pith:IX5BJV4W","schema_version":"1.0","canonical_sha256":"45fa14d796000cb05560e38f3a079d168be33a0b510df06dcce9c0a5b8e4e9a7","source":{"kind":"arxiv","id":"1708.02406","version":1},"attestation_state":"computed","paper":{"title":"Robust Conditional Probabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Yoav Wald","submitted_at":"2017-08-08T08:42:09Z","abstract_excerpt":"Conditional probabilities are a core concept in machine learning. For example, optimal prediction of a label $Y$ given an input $X$ corresponds to maximizing the conditional probability of $Y$ given $X$. A common approach to inference tasks is learning a model of conditional probabilities. However, these models are often based on strong assumptions (e.g., log-linear models), and hence their estimate of conditional probabilities is not robust and is highly dependent on the validity of their assumptions.\n  Here we propose a framework for reasoning about conditional probabilities without assuming"},"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":"1708.02406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T08:42:09Z","cross_cats_sorted":[],"title_canon_sha256":"08145191e47f973c7ea10ccf006b308b85f8735101ac5a79efe3357ed29004dd","abstract_canon_sha256":"90fbd33011e191bebbdde2185202b458a34073c8a72f0c6fecb82ea6bb63e197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:24.388835Z","signature_b64":"1o2dlC5EhZ4YWzJlSeoemVgWgpszU71QYpi9xBH0HvnPSOGcDJiPD8ToTGq16ONQOf3pC1OQ6MRaFEB2XQPDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45fa14d796000cb05560e38f3a079d168be33a0b510df06dcce9c0a5b8e4e9a7","last_reissued_at":"2026-05-18T00:38:24.388135Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:24.388135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Conditional Probabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Yoav Wald","submitted_at":"2017-08-08T08:42:09Z","abstract_excerpt":"Conditional probabilities are a core concept in machine learning. For example, optimal prediction of a label $Y$ given an input $X$ corresponds to maximizing the conditional probability of $Y$ given $X$. A common approach to inference tasks is learning a model of conditional probabilities. However, these models are often based on strong assumptions (e.g., log-linear models), and hence their estimate of conditional probabilities is not robust and is highly dependent on the validity of their assumptions.\n  Here we propose a framework for reasoning about conditional probabilities without assuming"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02406","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":""},"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":"1708.02406","created_at":"2026-05-18T00:38:24.388247+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.02406v1","created_at":"2026-05-18T00:38:24.388247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02406","created_at":"2026-05-18T00:38:24.388247+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX5BJV4WAAGL","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX5BJV4WAAGLAVLA","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX5BJV4W","created_at":"2026-05-18T12:31:21.493067+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/IX5BJV4WAAGLAVLA4OHTUB45C2","json":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2.json","graph_json":"https://pith.science/api/pith-number/IX5BJV4WAAGLAVLA4OHTUB45C2/graph.json","events_json":"https://pith.science/api/pith-number/IX5BJV4WAAGLAVLA4OHTUB45C2/events.json","paper":"https://pith.science/paper/IX5BJV4W"},"agent_actions":{"view_html":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2","download_json":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2.json","view_paper":"https://pith.science/paper/IX5BJV4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.02406&json=true","fetch_graph":"https://pith.science/api/pith-number/IX5BJV4WAAGLAVLA4OHTUB45C2/graph.json","fetch_events":"https://pith.science/api/pith-number/IX5BJV4WAAGLAVLA4OHTUB45C2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2/action/storage_attestation","attest_author":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2/action/author_attestation","sign_citation":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2/action/citation_signature","submit_replication":"https://pith.science/pith/IX5BJV4WAAGLAVLA4OHTUB45C2/action/replication_record"}},"created_at":"2026-05-18T00:38:24.388247+00:00","updated_at":"2026-05-18T00:38:24.388247+00:00"}