{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:2ESFZRKRAJFBQ6IMM5DNGNWUO5","short_pith_number":"pith:2ESFZRKR","canonical_record":{"source":{"id":"1506.04513","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T08:41:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a101eecb9b9d9cee9af9cb8c6144337e1eea7a891bd1558cc1edf210bde9152f","abstract_canon_sha256":"0b030b0145052bd97eeb639901a87581c5d4fc53a9b69dbc0e014d0f15348d1e"},"schema_version":"1.0"},"canonical_sha256":"d1245cc551024a18790c6746d336d4776500d96841e6ebd047ef38e57847ed05","source":{"kind":"arxiv","id":"1506.04513","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04513","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04513v1","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04513","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"2ESFZRKRAJFB","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"2ESFZRKRAJFBQ6IM","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"2ESFZRKR","created_at":"2026-05-18T12:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:2ESFZRKRAJFBQ6IMM5DNGNWUO5","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04513","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T08:41:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a101eecb9b9d9cee9af9cb8c6144337e1eea7a891bd1558cc1edf210bde9152f","abstract_canon_sha256":"0b030b0145052bd97eeb639901a87581c5d4fc53a9b69dbc0e014d0f15348d1e"},"schema_version":"1.0"},"canonical_sha256":"d1245cc551024a18790c6746d336d4776500d96841e6ebd047ef38e57847ed05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:49:30.975302Z","signature_b64":"qv7ryJUpH2c+TeKddBVL/LF+HSIJ0gcIMHt78gWxAqjjEg5qq1Q3m3nsnpxIvhWzQmzfFis0PovuNYI5biWdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1245cc551024a18790c6746d336d4776500d96841e6ebd047ef38e57847ed05","last_reissued_at":"2026-05-18T01:49:30.974544Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:49:30.974544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04513","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83kjjNPpsukqQtGSlqw1xiwNkzz66BN2vmial19xkiGY4AsLwJnEj/lvxsMB/UI0zT02cypLOwtYBZLpojA2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:08.638594Z"},"content_sha256":"978b9deb133cec7aca6a3d1f82e88cf925d306d376773f98ba4002c1a334f379","schema_version":"1.0","event_id":"sha256:978b9deb133cec7aca6a3d1f82e88cf925d306d376773f98ba4002c1a334f379"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:2ESFZRKRAJFBQ6IMM5DNGNWUO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Risk Minimization and Conditional Probability Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matus Telgarsky, Miroslav Dud\\'ik, Robert Schapire","submitted_at":"2015-06-15T08:41:39Z","abstract_excerpt":"This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any sequence of predictors minimizing convex risk over the source distribution will converge to this unique model when the class of predictors is linear (but potentially of infinite dimension). Secondly, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04513","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FjPzm218pOOWgsdXgjgSfThRiYcXbs6KGDdI4X6DrnoUUf/BXuQJumG7fljT/MUhteAT8Mo3RWau5cOceVggAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:08.639146Z"},"content_sha256":"5c52ec0e7d215b0e85949aaf1debdcd81016805cee956a2bce484b98d1e0e36f","schema_version":"1.0","event_id":"sha256:5c52ec0e7d215b0e85949aaf1debdcd81016805cee956a2bce484b98d1e0e36f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/bundle.json","state_url":"https://pith.science/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T21:28:08Z","links":{"resolver":"https://pith.science/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5","bundle":"https://pith.science/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/bundle.json","state":"https://pith.science/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ESFZRKRAJFBQ6IMM5DNGNWUO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:2ESFZRKRAJFBQ6IMM5DNGNWUO5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b030b0145052bd97eeb639901a87581c5d4fc53a9b69dbc0e014d0f15348d1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T08:41:39Z","title_canon_sha256":"a101eecb9b9d9cee9af9cb8c6144337e1eea7a891bd1558cc1edf210bde9152f"},"schema_version":"1.0","source":{"id":"1506.04513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04513","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04513v1","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04513","created_at":"2026-05-18T01:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"2ESFZRKRAJFB","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"2ESFZRKRAJFBQ6IM","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"2ESFZRKR","created_at":"2026-05-18T12:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:5c52ec0e7d215b0e85949aaf1debdcd81016805cee956a2bce484b98d1e0e36f","target":"graph","created_at":"2026-05-18T01:49:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any sequence of predictors minimizing convex risk over the source distribution will converge to this unique model when the class of predictors is linear (but potentially of infinite dimension). Secondly, we","authors_text":"Matus Telgarsky, Miroslav Dud\\'ik, Robert Schapire","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T08:41:39Z","title":"Convex Risk Minimization and Conditional Probability Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04513","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:978b9deb133cec7aca6a3d1f82e88cf925d306d376773f98ba4002c1a334f379","target":"record","created_at":"2026-05-18T01:49:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b030b0145052bd97eeb639901a87581c5d4fc53a9b69dbc0e014d0f15348d1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T08:41:39Z","title_canon_sha256":"a101eecb9b9d9cee9af9cb8c6144337e1eea7a891bd1558cc1edf210bde9152f"},"schema_version":"1.0","source":{"id":"1506.04513","kind":"arxiv","version":1}},"canonical_sha256":"d1245cc551024a18790c6746d336d4776500d96841e6ebd047ef38e57847ed05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1245cc551024a18790c6746d336d4776500d96841e6ebd047ef38e57847ed05","first_computed_at":"2026-05-18T01:49:30.974544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:49:30.974544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qv7ryJUpH2c+TeKddBVL/LF+HSIJ0gcIMHt78gWxAqjjEg5qq1Q3m3nsnpxIvhWzQmzfFis0PovuNYI5biWdDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:49:30.975302Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:978b9deb133cec7aca6a3d1f82e88cf925d306d376773f98ba4002c1a334f379","sha256:5c52ec0e7d215b0e85949aaf1debdcd81016805cee956a2bce484b98d1e0e36f"],"state_sha256":"517a6b378f73207860baf48d4a4f01be32db6b55733efa526fc5a057b75ef721"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJYqH9ghY5KzlkXRyEkcEtu2NQbGaQAHa80SvqLqFiZB7W8gljAH5neOF17327X0qrKav05TrRQ/Tebl9d1lDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:28:08.641210Z","bundle_sha256":"6fc2cc7ea7b187be69bbdb2bad2fbc1864540b867f10b3894ad7b3e9cb23c49c"}}