{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6YRNMN2EMSFQYAU4PK56DEF5GU","short_pith_number":"pith:6YRNMN2E","schema_version":"1.0","canonical_sha256":"f622d63744648b0c029c7abbe190bd3509cdcb552d119461be6200bd923aa7ef","source":{"kind":"arxiv","id":"2605.02099","version":2},"attestation_state":"computed","paper":{"title":"Entropic Strict Minimum Message Length and Its Connections to PAC-Bayes and NML","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Entropic SMML generalizes strict minimum message length into a tunable family that interpolates between Bayesian and minimax coding.","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Daniel F. Schmidt, Enes Makalic","submitted_at":"2026-05-03T23:38:19Z","abstract_excerpt":"We introduce entropic strict minimum message length (SMML), a risk-sensitive generalization of strict minimum message length coding. The proposed criterion replaces expected two-part codelength under the prior predictive distribution with an exponential certainty equivalent, thereby defining a one-parameter family of coding rules that interpolates between Bayesian average-case coding and worst-case minimax coding. We show that ordinary SMML is recovered in the risk-neutral limit, while the extreme risk-sensitive limit yields a minimax codelength criterion; when centered by the oracle maximum l"},"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":true},"canonical_record":{"source":{"id":"2605.02099","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-05-03T23:38:19Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"84873b3a30d08b4f73d3cb7a54b01efa0e77edb25746b829ac58c66a564750f1","abstract_canon_sha256":"87d39ae688331f7d4099c11e22b306fff206253ef0a9180a56f9552ebed52ad2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:15.187772Z","signature_b64":"uE4+GTufBRwkbAn7ZtT8r68fd4EFiViO8+HcDbDr1GE175Yod6FLt3Ct0QNveVuhlBSbXd3GxARovqQtTe6KDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f622d63744648b0c029c7abbe190bd3509cdcb552d119461be6200bd923aa7ef","last_reissued_at":"2026-05-20T01:05:15.187082Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:15.187082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropic Strict Minimum Message Length and Its Connections to PAC-Bayes and NML","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Entropic SMML generalizes strict minimum message length into a tunable family that interpolates between Bayesian and minimax coding.","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Daniel F. Schmidt, Enes Makalic","submitted_at":"2026-05-03T23:38:19Z","abstract_excerpt":"We introduce entropic strict minimum message length (SMML), a risk-sensitive generalization of strict minimum message length coding. The proposed criterion replaces expected two-part codelength under the prior predictive distribution with an exponential certainty equivalent, thereby defining a one-parameter family of coding rules that interpolates between Bayesian average-case coding and worst-case minimax coding. We show that ordinary SMML is recovered in the risk-neutral limit, while the extreme risk-sensitive limit yields a minimax codelength criterion; when centered by the oracle maximum l"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that entropic SMML admits a variational characterization as a Kullback--Leibler-regularized worst-case expected codelength, giving it a PAC--Bayes-type interpretation. We establish a joint asymptotic theory linking the sample size n and the risk parameter τ, showing that in regular parametric models the transition between Bayesian, robust, and minimax coding regimes occurs on a logarithmic scale.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The joint asymptotic theory and the affine partition property hold only under the assumption of regular parametric models and regular exponential families; the paper does not specify how the results degrade when these regularity conditions are violated.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Entropic SMML defines a risk-sensitive family of coding rules bridging Bayesian MML, PAC-Bayes, and NML minimax-regret via exponential certainty equivalents and tilted centroids in exponential families.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Entropic SMML generalizes strict minimum message length into a tunable family that interpolates between Bayesian and minimax coding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cb055e2b13d48f69399c2650771879fb50558b86b5d9366068de73cfb85fb815"},"source":{"id":"2605.02099","kind":"arxiv","version":2},"verdict":{"id":"b0d8d8d8-63db-4f65-9622-d5f2c71a9c5d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:36:25.767126Z","strongest_claim":"We show that entropic SMML admits a variational characterization as a Kullback--Leibler-regularized worst-case expected codelength, giving it a PAC--Bayes-type interpretation. We establish a joint asymptotic theory linking the sample size n and the risk parameter τ, showing that in regular parametric models the transition between Bayesian, robust, and minimax coding regimes occurs on a logarithmic scale.","one_line_summary":"Entropic SMML defines a risk-sensitive family of coding rules bridging Bayesian MML, PAC-Bayes, and NML minimax-regret via exponential certainty equivalents and tilted centroids in exponential families.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The joint asymptotic theory and the affine partition property hold only under the assumption of regular parametric models and regular exponential families; the paper does not specify how the results degrade when these regularity conditions are violated.","pith_extraction_headline":"Entropic SMML generalizes strict minimum message length into a tunable family that interpolates between Bayesian and minimax coding."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02099/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:40:11.652073Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e212b1dae4db6e6d3b8118052cb7499db5e42d25b8a0ca3e0c133ab9341bcb17"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"d94df8091ecbe77559d3eb3f23d5b130ba926bf6168773176b72a6709bc542eb"},"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":"2605.02099","created_at":"2026-05-20T01:05:15.187197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.02099v2","created_at":"2026-05-20T01:05:15.187197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02099","created_at":"2026-05-20T01:05:15.187197+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YRNMN2EMSFQ","created_at":"2026-05-20T01:05:15.187197+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YRNMN2EMSFQYAU4","created_at":"2026-05-20T01:05:15.187197+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YRNMN2E","created_at":"2026-05-20T01:05:15.187197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU","json":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU.json","graph_json":"https://pith.science/api/pith-number/6YRNMN2EMSFQYAU4PK56DEF5GU/graph.json","events_json":"https://pith.science/api/pith-number/6YRNMN2EMSFQYAU4PK56DEF5GU/events.json","paper":"https://pith.science/paper/6YRNMN2E"},"agent_actions":{"view_html":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU","download_json":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU.json","view_paper":"https://pith.science/paper/6YRNMN2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.02099&json=true","fetch_graph":"https://pith.science/api/pith-number/6YRNMN2EMSFQYAU4PK56DEF5GU/graph.json","fetch_events":"https://pith.science/api/pith-number/6YRNMN2EMSFQYAU4PK56DEF5GU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU/action/storage_attestation","attest_author":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU/action/author_attestation","sign_citation":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU/action/citation_signature","submit_replication":"https://pith.science/pith/6YRNMN2EMSFQYAU4PK56DEF5GU/action/replication_record"}},"created_at":"2026-05-20T01:05:15.187197+00:00","updated_at":"2026-05-20T01:05:15.187197+00:00"}