{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KPHNJMADO4OTXJRWUEGRPUJFVM","short_pith_number":"pith:KPHNJMAD","schema_version":"1.0","canonical_sha256":"53ced4b003771d3ba636a10d17d125ab33a4c1de574cc8deeaec97bf35618839","source":{"kind":"arxiv","id":"1705.01166","version":3},"attestation_state":"computed","paper":{"title":"Maximizing the information learned from finite data selects a simple model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"physics.data-an","authors_text":"Benjamin B. Machta, Henry H. Mattingly, Mark K. Transtrum, Michael C. Abbott","submitted_at":"2017-05-02T20:27:14Z","abstract_excerpt":"We use the language of uninformative Bayesian prior choice to study the selection of appropriately simple effective models. We advocate for the prior which maximizes the mutual information between parameters and predictions, learning as much as possible from limited data. When many parameters are poorly constrained by the available data, we find that this prior puts weight only on boundaries of the parameter manifold. Thus it selects a lower-dimensional effective theory in a principled way, ignoring irrelevant parameter directions. In the limit where there is sufficient data to tightly constra"},"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":false},"canonical_record":{"source":{"id":"1705.01166","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2017-05-02T20:27:14Z","cross_cats_sorted":["cond-mat.stat-mech","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"8c0092e416365b19b5569552c976000a5c6d91a63266a6d41d01a2e0b19b53f9","abstract_canon_sha256":"423e83146cbc72b48aa6bf09b49e99813382491635b44f9ebeb849d0271d304a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:16.919724Z","signature_b64":"BzyU+VNfRvUpUs6KBKOuWIsV1+rR/ErdkrRpS938TzfYpAL0v+BSLrRBnlZUoOC9QogERkE5ZgfrYeZSsjBvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ced4b003771d3ba636a10d17d125ab33a4c1de574cc8deeaec97bf35618839","last_reissued_at":"2026-05-18T00:23:16.918930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:16.918930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximizing the information learned from finite data selects a simple model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"physics.data-an","authors_text":"Benjamin B. Machta, Henry H. Mattingly, Mark K. Transtrum, Michael C. Abbott","submitted_at":"2017-05-02T20:27:14Z","abstract_excerpt":"We use the language of uninformative Bayesian prior choice to study the selection of appropriately simple effective models. We advocate for the prior which maximizes the mutual information between parameters and predictions, learning as much as possible from limited data. When many parameters are poorly constrained by the available data, we find that this prior puts weight only on boundaries of the parameter manifold. Thus it selects a lower-dimensional effective theory in a principled way, ignoring irrelevant parameter directions. In the limit where there is sufficient data to tightly constra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01166","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.01166","created_at":"2026-05-18T00:23:16.919057+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.01166v3","created_at":"2026-05-18T00:23:16.919057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01166","created_at":"2026-05-18T00:23:16.919057+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPHNJMADO4OT","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPHNJMADO4OTXJRW","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPHNJMAD","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM","json":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM.json","graph_json":"https://pith.science/api/pith-number/KPHNJMADO4OTXJRWUEGRPUJFVM/graph.json","events_json":"https://pith.science/api/pith-number/KPHNJMADO4OTXJRWUEGRPUJFVM/events.json","paper":"https://pith.science/paper/KPHNJMAD"},"agent_actions":{"view_html":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM","download_json":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM.json","view_paper":"https://pith.science/paper/KPHNJMAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.01166&json=true","fetch_graph":"https://pith.science/api/pith-number/KPHNJMADO4OTXJRWUEGRPUJFVM/graph.json","fetch_events":"https://pith.science/api/pith-number/KPHNJMADO4OTXJRWUEGRPUJFVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM/action/storage_attestation","attest_author":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM/action/author_attestation","sign_citation":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM/action/citation_signature","submit_replication":"https://pith.science/pith/KPHNJMADO4OTXJRWUEGRPUJFVM/action/replication_record"}},"created_at":"2026-05-18T00:23:16.919057+00:00","updated_at":"2026-05-18T00:23:16.919057+00:00"}