{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3GG6T5VFRU2XQ4J7WMGSIJ2RBF","short_pith_number":"pith:3GG6T5VF","canonical_record":{"source":{"id":"1805.03804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-10T04:03:34Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"1e8a1883048c68a7c293378425b76f1a5589afaada0ba2cc41c6db6717178193","abstract_canon_sha256":"06ccbab56e7772f9b904796008c9b17d41d5d16dac15d8b4c501e1e7fe593734"},"schema_version":"1.0"},"canonical_sha256":"d98de9f6a58d3578713fb30d2427510940be52c5cfdb4c67ac158f41f2fbbaae","source":{"kind":"arxiv","id":"1805.03804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03804","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03804v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03804","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"3GG6T5VFRU2X","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GG6T5VFRU2XQ4J7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GG6T5VF","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3GG6T5VFRU2XQ4J7WMGSIJ2RBF","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-10T04:03:34Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"1e8a1883048c68a7c293378425b76f1a5589afaada0ba2cc41c6db6717178193","abstract_canon_sha256":"06ccbab56e7772f9b904796008c9b17d41d5d16dac15d8b4c501e1e7fe593734"},"schema_version":"1.0"},"canonical_sha256":"d98de9f6a58d3578713fb30d2427510940be52c5cfdb4c67ac158f41f2fbbaae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:18.715714Z","signature_b64":"5JEoVgLfW3XuET32+a56IWNPn7WskaaqYBzN9vv+60gBp8EHEqEXi6hqDOY0lBCtYWqQhiQratz0gm3w+VvmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98de9f6a58d3578713fb30d2427510940be52c5cfdb4c67ac158f41f2fbbaae","last_reissued_at":"2026-05-18T00:16:18.715122Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:18.715122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03804","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8y+1Ep7YeNzCmJIsVrXTtRghGnUSkQe0CcG2ZhRUWtMGhL6Zk9LqE5aS2W3KkZWqm3lk1EALtjqXu64OmwXMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:22:34.458342Z"},"content_sha256":"042b55e0ca6b50f6ba31d7e993c972a497d3fec6fa4a207f5b9bf346c72cae1a","schema_version":"1.0","event_id":"sha256:042b55e0ca6b50f6ba31d7e993c972a497d3fec6fa4a207f5b9bf346c72cae1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3GG6T5VFRU2XQ4J7WMGSIJ2RBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Universality of the Logistic Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Amichai Painsky, Gregory W. Wornell","submitted_at":"2018-05-10T04:03:34Z","abstract_excerpt":"A loss function measures the discrepancy between the true values (observations) and their estimated fits, for a given instance of data. A loss function is said to be proper (unbiased, Fisher consistent) if the fits are defined over a unit simplex, and the minimizer of the expected loss is the true underlying probability of the data. Typical examples are the zero-one loss, the quadratic loss and the Bernoulli log-likelihood loss (log-loss). In this work we show that for binary classification problems, the divergence associated with smooth, proper and convex loss functions is bounded from above "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03804","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Seuxnppr9k2oojpd8NmosTI3RppnDZluVVnxyRhA/4/bJ6156xvq64kHnC3klRKFOjWbSkNwqJ0iQzGBFbEaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:22:34.459094Z"},"content_sha256":"bc1894cdb80f469a3f66b3b0de20ae40e2e3171b2e8b1cc46639faa1c097debd","schema_version":"1.0","event_id":"sha256:bc1894cdb80f469a3f66b3b0de20ae40e2e3171b2e8b1cc46639faa1c097debd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/bundle.json","state_url":"https://pith.science/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/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":"2026-05-31T17:22:34Z","links":{"resolver":"https://pith.science/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF","bundle":"https://pith.science/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/bundle.json","state":"https://pith.science/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GG6T5VFRU2XQ4J7WMGSIJ2RBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3GG6T5VFRU2XQ4J7WMGSIJ2RBF","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":"06ccbab56e7772f9b904796008c9b17d41d5d16dac15d8b4c501e1e7fe593734","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-10T04:03:34Z","title_canon_sha256":"1e8a1883048c68a7c293378425b76f1a5589afaada0ba2cc41c6db6717178193"},"schema_version":"1.0","source":{"id":"1805.03804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03804","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03804v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03804","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"3GG6T5VFRU2X","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3GG6T5VFRU2XQ4J7","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3GG6T5VF","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:bc1894cdb80f469a3f66b3b0de20ae40e2e3171b2e8b1cc46639faa1c097debd","target":"graph","created_at":"2026-05-18T00:16:18Z","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":"A loss function measures the discrepancy between the true values (observations) and their estimated fits, for a given instance of data. A loss function is said to be proper (unbiased, Fisher consistent) if the fits are defined over a unit simplex, and the minimizer of the expected loss is the true underlying probability of the data. Typical examples are the zero-one loss, the quadratic loss and the Bernoulli log-likelihood loss (log-loss). In this work we show that for binary classification problems, the divergence associated with smooth, proper and convex loss functions is bounded from above ","authors_text":"Amichai Painsky, Gregory W. Wornell","cross_cats":["math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-10T04:03:34Z","title":"On the Universality of the Logistic Loss Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03804","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":"sha256:042b55e0ca6b50f6ba31d7e993c972a497d3fec6fa4a207f5b9bf346c72cae1a","target":"record","created_at":"2026-05-18T00:16:18Z","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":"06ccbab56e7772f9b904796008c9b17d41d5d16dac15d8b4c501e1e7fe593734","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-05-10T04:03:34Z","title_canon_sha256":"1e8a1883048c68a7c293378425b76f1a5589afaada0ba2cc41c6db6717178193"},"schema_version":"1.0","source":{"id":"1805.03804","kind":"arxiv","version":1}},"canonical_sha256":"d98de9f6a58d3578713fb30d2427510940be52c5cfdb4c67ac158f41f2fbbaae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98de9f6a58d3578713fb30d2427510940be52c5cfdb4c67ac158f41f2fbbaae","first_computed_at":"2026-05-18T00:16:18.715122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:18.715122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5JEoVgLfW3XuET32+a56IWNPn7WskaaqYBzN9vv+60gBp8EHEqEXi6hqDOY0lBCtYWqQhiQratz0gm3w+VvmCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:18.715714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:042b55e0ca6b50f6ba31d7e993c972a497d3fec6fa4a207f5b9bf346c72cae1a","sha256:bc1894cdb80f469a3f66b3b0de20ae40e2e3171b2e8b1cc46639faa1c097debd"],"state_sha256":"d7d833797868321b26c96b4ec49aa8470f748283500c26adf1bc9f815b1c2716"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XuauHQPctb5l54m5X/57yWVSG3T/J/wHveiufxwLXYdpv5/u8n9n63UbrRpdf66y++lCDwOxC7N/jNKUVoLbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:22:34.462987Z","bundle_sha256":"f1aa2666fd6aada25f284320e409b8df43fdf128c803cd038c4729f02f502914"}}