{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WBCDH5NP56S2ZRYSWSE2FREJJW","short_pith_number":"pith:WBCDH5NP","canonical_record":{"source":{"id":"2304.09424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:16:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4434de8412c35baad95e446434ddac3c6d4a4691db41aafc69e31fc7c7093cac","abstract_canon_sha256":"8ab306a011797026ab7e693f58ac3876456ea824866a0cf4e4b7a1c582f84c8f"},"schema_version":"1.0"},"canonical_sha256":"b04433f5afefa5acc712b489a2c4894da4d8e72c3fb783dca8599d44049fedae","source":{"kind":"arxiv","id":"2304.09424","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09424","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09424v2","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09424","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"WBCDH5NP56S2","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"WBCDH5NP56S2ZRYS","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"WBCDH5NP","created_at":"2026-07-05T07:21:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WBCDH5NP56S2ZRYSWSE2FREJJW","target":"record","payload":{"canonical_record":{"source":{"id":"2304.09424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:16:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4434de8412c35baad95e446434ddac3c6d4a4691db41aafc69e31fc7c7093cac","abstract_canon_sha256":"8ab306a011797026ab7e693f58ac3876456ea824866a0cf4e4b7a1c582f84c8f"},"schema_version":"1.0"},"canonical_sha256":"b04433f5afefa5acc712b489a2c4894da4d8e72c3fb783dca8599d44049fedae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:41.411512Z","signature_b64":"h8KrreyAxIkMt6om2Jm0BR95+SUikb4Fvo6K+Mz3oUSvfjpO8klexiiVUWM4hPCz/GkcbibSMFSlRBZbVYL3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b04433f5afefa5acc712b489a2c4894da4d8e72c3fb783dca8599d44049fedae","last_reissued_at":"2026-07-05T07:21:41.411055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:41.411055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.09424","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Pjz3DdyB7QGuPJ2u74Gfn7YktQsr7v1JGL/gh5Lw1KFcsJQ3NCtGRZVv3ZioVlmfJW7q6molkcJivqpT+NXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:45.161842Z"},"content_sha256":"ae0719757e686a1a316fe819c6aaf539cacd0edd53c1dbdec2cfa83194a38835","schema_version":"1.0","event_id":"sha256:ae0719757e686a1a316fe819c6aaf539cacd0edd53c1dbdec2cfa83194a38835"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WBCDH5NP56S2ZRYSWSE2FREJJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loss Minimization Yields Multicalibration for Large Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Tauman Kalai, Jaros{\\l}aw B{\\l}asiok, Lunjia Hu, Parikshit Gopalan, Preetum Nakkiran","submitted_at":"2023-04-19T05:16:20Z","abstract_excerpt":"Multicalibration is a notion of fairness for predictors that requires them to provide calibrated predictions across a large set of protected groups. Multicalibration is known to be a distinct goal than loss minimization, even for simple predictors such as linear functions.\n  In this work, we consider the setting where the protected groups can be represented by neural networks of size $k$, and the predictors are neural networks of size $n > k$. We show that minimizing the squared loss over all neural nets of size $n$ implies multicalibration for all but a bounded number of unlucky values of $n$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09424","kind":"arxiv","version":2},"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/2304.09424/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCUAiwdQMdHm4oGfba/EMNZZ2wcEOPasc7gy3W5NUSzZgqUfOPCvx6CdbwvrMAN7S7H1sAmOJyCguDSqW0WDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:45.162380Z"},"content_sha256":"1bad9aa39a0ccc377dafb8aae05feaee03368657aa814efb97f3b1b966ef395c","schema_version":"1.0","event_id":"sha256:1bad9aa39a0ccc377dafb8aae05feaee03368657aa814efb97f3b1b966ef395c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/bundle.json","state_url":"https://pith.science/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/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":"2026-08-08T06:58:45Z","links":{"resolver":"https://pith.science/pith/WBCDH5NP56S2ZRYSWSE2FREJJW","bundle":"https://pith.science/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/bundle.json","state":"https://pith.science/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBCDH5NP56S2ZRYSWSE2FREJJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WBCDH5NP56S2ZRYSWSE2FREJJW","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":"8ab306a011797026ab7e693f58ac3876456ea824866a0cf4e4b7a1c582f84c8f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:16:20Z","title_canon_sha256":"4434de8412c35baad95e446434ddac3c6d4a4691db41aafc69e31fc7c7093cac"},"schema_version":"1.0","source":{"id":"2304.09424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09424","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09424v2","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09424","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"WBCDH5NP56S2","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"WBCDH5NP56S2ZRYS","created_at":"2026-07-05T07:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"WBCDH5NP","created_at":"2026-07-05T07:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:1bad9aa39a0ccc377dafb8aae05feaee03368657aa814efb97f3b1b966ef395c","target":"graph","created_at":"2026-07-05T07:21:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.09424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multicalibration is a notion of fairness for predictors that requires them to provide calibrated predictions across a large set of protected groups. Multicalibration is known to be a distinct goal than loss minimization, even for simple predictors such as linear functions.\n  In this work, we consider the setting where the protected groups can be represented by neural networks of size $k$, and the predictors are neural networks of size $n > k$. We show that minimizing the squared loss over all neural nets of size $n$ implies multicalibration for all but a bounded number of unlucky values of $n$","authors_text":"Adam Tauman Kalai, Jaros{\\l}aw B{\\l}asiok, Lunjia Hu, Parikshit Gopalan, Preetum Nakkiran","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:16:20Z","title":"Loss Minimization Yields Multicalibration for Large Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09424","kind":"arxiv","version":2},"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:ae0719757e686a1a316fe819c6aaf539cacd0edd53c1dbdec2cfa83194a38835","target":"record","created_at":"2026-07-05T07:21:41Z","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":"8ab306a011797026ab7e693f58ac3876456ea824866a0cf4e4b7a1c582f84c8f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:16:20Z","title_canon_sha256":"4434de8412c35baad95e446434ddac3c6d4a4691db41aafc69e31fc7c7093cac"},"schema_version":"1.0","source":{"id":"2304.09424","kind":"arxiv","version":2}},"canonical_sha256":"b04433f5afefa5acc712b489a2c4894da4d8e72c3fb783dca8599d44049fedae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b04433f5afefa5acc712b489a2c4894da4d8e72c3fb783dca8599d44049fedae","first_computed_at":"2026-07-05T07:21:41.411055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:41.411055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h8KrreyAxIkMt6om2Jm0BR95+SUikb4Fvo6K+Mz3oUSvfjpO8klexiiVUWM4hPCz/GkcbibSMFSlRBZbVYL3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:41.411512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.09424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae0719757e686a1a316fe819c6aaf539cacd0edd53c1dbdec2cfa83194a38835","sha256:1bad9aa39a0ccc377dafb8aae05feaee03368657aa814efb97f3b1b966ef395c"],"state_sha256":"5d9d911b43e8dc6c2ff8848cbe89068d90ea3571d33c2e393a35e7df427965b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kNB47IIH7GPngFVW2QefT/vfUxv7gtTSY0ePqMdw5PO4xcqGNL4jOyfEKxrjPdnmqfBG0UR25isRtdjUgCYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:58:45.167954Z","bundle_sha256":"4563298fb91bf1767c9069f6687690219d9c50e5f884bb23185526daa3c8bdf9"}}