{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DV77N3Z6KGTSQY263GKKNPQRMM","short_pith_number":"pith:DV77N3Z6","canonical_record":{"source":{"id":"2605.07107","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-05-08T01:34:03Z","cross_cats_sorted":["math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2a4a680a09694c437271b2b184fca019a9842b1c3e38d77f082eaaaca661a2b3","abstract_canon_sha256":"4e55b01d60d7984c861fde8e37603440842a5053e72ed8344eb54fa49f1a3e69"},"schema_version":"1.0"},"canonical_sha256":"1d7ff6ef3e51a728635ed994a6be116337c4b59d4973c81ae591927112896d12","source":{"kind":"arxiv","id":"2605.07107","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07107","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07107v2","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07107","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_12","alias_value":"DV77N3Z6KGTS","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_16","alias_value":"DV77N3Z6KGTSQY26","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_8","alias_value":"DV77N3Z6","created_at":"2026-05-26T01:02:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DV77N3Z6KGTSQY263GKKNPQRMM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.07107","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-05-08T01:34:03Z","cross_cats_sorted":["math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2a4a680a09694c437271b2b184fca019a9842b1c3e38d77f082eaaaca661a2b3","abstract_canon_sha256":"4e55b01d60d7984c861fde8e37603440842a5053e72ed8344eb54fa49f1a3e69"},"schema_version":"1.0"},"canonical_sha256":"1d7ff6ef3e51a728635ed994a6be116337c4b59d4973c81ae591927112896d12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:35.461528Z","signature_b64":"rovyAPeg4S6L2DTBx7CajWMgQrMdnurkBDfUmy+eus8OqWBFBXSk+Mf00+GqOIcztNfGdLVvRHOEJjle5M0uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7ff6ef3e51a728635ed994a6be116337c4b59d4973c81ae591927112896d12","last_reissued_at":"2026-05-26T01:02:35.460660Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:35.460660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.07107","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":"2026-05-26T01:02:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhVmKW/lrNenA4zdcgxap/R71hApCx1gNdgWL77Ks+wB8z5Z+mXfjoEtYfnZp81JuXyFLNf/bV57Vs8tEFJ7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:26:17.025362Z"},"content_sha256":"97bf02438015155a8bba6f18dbbeb0f11102fe33787db116a68f6a59326e4bed","schema_version":"1.0","event_id":"sha256:97bf02438015155a8bba6f18dbbeb0f11102fe33787db116a68f6a59326e4bed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DV77N3Z6KGTSQY263GKKNPQRMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score.","cross_cats":["math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.IT","authors_text":"Alex Dytso, Leighton P. Barnes","submitted_at":"2026-05-08T01:34:03Z","abstract_excerpt":"It is well known that, under standard regularity conditions, the maximum likelihood estimator (MLE) satisfies a central limit theorem and converges in distribution to a Gaussian random variable as the sample size grows. This paper strengthens this classical result by developing several stronger forms of asymptotic normality for the normalized MLE. With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing convergence in relative entropy to the limiting Gaussian law. When the Fisher information of the normalized estimate is bounded, or its density has bounded first derivative, we further show that the smoothing can be removed, yielding entropic normality of the MLE itself.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Additional assumptions on the score function (beyond standard regularity conditions for the classical CLT), plus bounded Fisher information or bounded first derivative of the density to remove smoothing; these are invoked to obtain the sub-Gaussian and entropic results.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cea1aef7eb739aae775a437d1a0160716ab0a6c6e52c4ef1edc057d563f19b93"},"source":{"id":"2605.07107","kind":"arxiv","version":2},"verdict":{"id":"c985ce6d-5ed7-4bd0-a190-0d671f598640","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:03:38.122694Z","strongest_claim":"With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing convergence in relative entropy to the limiting Gaussian law. When the Fisher information of the normalized estimate is bounded, or its density has bounded first derivative, we further show that the smoothing can be removed, yielding entropic normality of the MLE itself.","one_line_summary":"Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Additional assumptions on the score function (beyond standard regularity conditions for the classical CLT), plus bounded Fisher information or bounded first derivative of the density to remove smoothing; these are invoked to obtain the sub-Gaussian and entropic results.","pith_extraction_headline":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07107/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:22:03.417955Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:36:21.924088Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.503626Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:03:17.240268Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1ff440977e43f8d191145e5661e3abfd5396adcd7c55a119f673340e5e3cac74"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46fdcb0783d1133a00e690c2eb6eb0e3c993ec863e4dfeb22b0eb1926f1b94a7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c985ce6d-5ed7-4bd0-a190-0d671f598640"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"We+K9GnRrwLpRr7VlOjvz9/PzC7ksGOwYr9RzbT1ToXxGJI/LGR2AplKXMZDeurNfHQgX5oD+dOcv6hJsXe7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:26:17.025928Z"},"content_sha256":"3c0acf1232a19766141b87380d4a6edac0a7f1b8b9611db3e01eee6ea1113894","schema_version":"1.0","event_id":"sha256:3c0acf1232a19766141b87380d4a6edac0a7f1b8b9611db3e01eee6ea1113894"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DV77N3Z6KGTSQY263GKKNPQRMM/bundle.json","state_url":"https://pith.science/pith/DV77N3Z6KGTSQY263GKKNPQRMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DV77N3Z6KGTSQY263GKKNPQRMM/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":"2026-06-01T16:26:17Z","links":{"resolver":"https://pith.science/pith/DV77N3Z6KGTSQY263GKKNPQRMM","bundle":"https://pith.science/pith/DV77N3Z6KGTSQY263GKKNPQRMM/bundle.json","state":"https://pith.science/pith/DV77N3Z6KGTSQY263GKKNPQRMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DV77N3Z6KGTSQY263GKKNPQRMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DV77N3Z6KGTSQY263GKKNPQRMM","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":"4e55b01d60d7984c861fde8e37603440842a5053e72ed8344eb54fa49f1a3e69","cross_cats_sorted":["math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-05-08T01:34:03Z","title_canon_sha256":"2a4a680a09694c437271b2b184fca019a9842b1c3e38d77f082eaaaca661a2b3"},"schema_version":"1.0","source":{"id":"2605.07107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07107","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07107v2","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07107","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_12","alias_value":"DV77N3Z6KGTS","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_16","alias_value":"DV77N3Z6KGTSQY26","created_at":"2026-05-26T01:02:35Z"},{"alias_kind":"pith_short_8","alias_value":"DV77N3Z6","created_at":"2026-05-26T01:02:35Z"}],"graph_snapshots":[{"event_id":"sha256:3c0acf1232a19766141b87380d4a6edac0a7f1b8b9611db3e01eee6ea1113894","target":"graph","created_at":"2026-05-26T01:02:35Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing convergence in relative entropy to the limiting Gaussian law. When the Fisher information of the normalized estimate is bounded, or its density has bounded first derivative, we further show that the smoothing can be removed, yielding entropic normality of the MLE itself."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Additional assumptions on the score function (beyond standard regularity conditions for the classical CLT), plus bounded Fisher information or bounded first derivative of the density to remove smoothing; these are invoked to obtain the sub-Gaussian and entropic results."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score."}],"snapshot_sha256":"cea1aef7eb739aae775a437d1a0160716ab0a6c6e52c4ef1edc057d563f19b93"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46fdcb0783d1133a00e690c2eb6eb0e3c993ec863e4dfeb22b0eb1926f1b94a7"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T11:22:03.417955Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T06:36:21.924088Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.503626Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T12:03:17.240268Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.07107/integrity.json","findings":[],"snapshot_sha256":"1ff440977e43f8d191145e5661e3abfd5396adcd7c55a119f673340e5e3cac74","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well known that, under standard regularity conditions, the maximum likelihood estimator (MLE) satisfies a central limit theorem and converges in distribution to a Gaussian random variable as the sample size grows. This paper strengthens this classical result by developing several stronger forms of asymptotic normality for the normalized MLE. With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing","authors_text":"Alex Dytso, Leighton P. Barnes","cross_cats":["math.IT","math.ST","stat.ML","stat.TH"],"headline":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-05-08T01:34:03Z","title":"Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07107","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T01:03:38.122694Z","id":"c985ce6d-5ed7-4bd0-a190-0d671f598640","model_set":{"reader":"grok-4.3"},"one_line_summary":"Under regularity conditions plus assumptions on the score, the normalized MLE has sub-Gaussian tails, all moments converge, and the estimator converges in relative entropy to Gaussian when Fisher information is bounded or the density has bounded derivative.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The normalized maximum likelihood estimator satisfies sub-Gaussian tail bounds and converges in relative entropy to a Gaussian under assumptions on the score.","strongest_claim":"With additional assumptions on the score, we first establish sub-Gaussian tail bounds and convergence of all moments for the normalized estimation error. We then prove an entropic central limit theorem for a smoothed version of the estimator, showing convergence in relative entropy to the limiting Gaussian law. When the Fisher information of the normalized estimate is bounded, or its density has bounded first derivative, we further show that the smoothing can be removed, yielding entropic normality of the MLE itself.","weakest_assumption":"Additional assumptions on the score function (beyond standard regularity conditions for the classical CLT), plus bounded Fisher information or bounded first derivative of the density to remove smoothing; these are invoked to obtain the sub-Gaussian and entropic results."}},"verdict_id":"c985ce6d-5ed7-4bd0-a190-0d671f598640"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:97bf02438015155a8bba6f18dbbeb0f11102fe33787db116a68f6a59326e4bed","target":"record","created_at":"2026-05-26T01:02:35Z","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":"4e55b01d60d7984c861fde8e37603440842a5053e72ed8344eb54fa49f1a3e69","cross_cats_sorted":["math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-05-08T01:34:03Z","title_canon_sha256":"2a4a680a09694c437271b2b184fca019a9842b1c3e38d77f082eaaaca661a2b3"},"schema_version":"1.0","source":{"id":"2605.07107","kind":"arxiv","version":2}},"canonical_sha256":"1d7ff6ef3e51a728635ed994a6be116337c4b59d4973c81ae591927112896d12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d7ff6ef3e51a728635ed994a6be116337c4b59d4973c81ae591927112896d12","first_computed_at":"2026-05-26T01:02:35.460660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:35.460660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rovyAPeg4S6L2DTBx7CajWMgQrMdnurkBDfUmy+eus8OqWBFBXSk+Mf00+GqOIcztNfGdLVvRHOEJjle5M0uDQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:35.461528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97bf02438015155a8bba6f18dbbeb0f11102fe33787db116a68f6a59326e4bed","sha256:3c0acf1232a19766141b87380d4a6edac0a7f1b8b9611db3e01eee6ea1113894"],"state_sha256":"eb8195212d1b0b700a1c67b4974d19ff31f5221e6863dbf38dd1a561ea0b2eea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0hwSKaRHYC2u+I0BHCaLlo5E4l7Xz5qT5gZtZzHeE+FsUyDc8QHlwoj7dS2FcpLynwGc+9HkqXxlZ4Rg0w9IBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:26:17.028241Z","bundle_sha256":"4fffe2d36c75d0fa07375f8cb2c52c0c7127cdd2125c9d938493956ae45fc6b6"}}