{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:REJG5FYRH6T2FU3A2Q4SMJME4M","short_pith_number":"pith:REJG5FYR","schema_version":"1.0","canonical_sha256":"89126e97113fa7a2d360d439262584e33dc00c83a9924fb49619eef43c8289a7","source":{"kind":"arxiv","id":"1609.03543","version":5},"attestation_state":"computed","paper":{"title":"Logical Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","math.LO","math.PR"],"primary_cat":"cs.AI","authors_text":"Andrew Critch, Jessica Taylor, Nate Soares, Scott Garrabrant, Tsvi Benson-Tilsen","submitted_at":"2016-09-12T19:30:56Z","abstract_excerpt":"We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations, and its own probabilities. We show that our algorithm, an instance of what we call a logical inductor, satisfies a number of intuitive desiderata, including: (1) it learns to predict patterns of truth and falsehood in logical statements, oft"},"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":"1609.03543","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-12T19:30:56Z","cross_cats_sorted":["cs.LO","math.LO","math.PR"],"title_canon_sha256":"928023ff8b9770fedc577c3f9395eaa87034c77f5d737f8925e443fe98f63807","abstract_canon_sha256":"b2b3d9b99ac64683ea4d8db037dc5a0bf71d8fff50277b06acacd67f58ca4ee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:35.630387Z","signature_b64":"SUxLkGjZlH7fgss7XQn9Br6uV8k2c4ScMGiLorSeeQwvVJIz8JYbfrKPPtpSp4JgUoiOG3SlGs32IIzpbo7YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89126e97113fa7a2d360d439262584e33dc00c83a9924fb49619eef43c8289a7","last_reissued_at":"2026-07-05T01:57:35.629850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:35.629850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logical Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","math.LO","math.PR"],"primary_cat":"cs.AI","authors_text":"Andrew Critch, Jessica Taylor, Nate Soares, Scott Garrabrant, Tsvi Benson-Tilsen","submitted_at":"2016-09-12T19:30:56Z","abstract_excerpt":"We present a computable algorithm that assigns probabilities to every logical statement in a given formal language, and refines those probabilities over time. For instance, if the language is Peano arithmetic, it assigns probabilities to all arithmetical statements, including claims about the twin prime conjecture, the outputs of long-running computations, and its own probabilities. We show that our algorithm, an instance of what we call a logical inductor, satisfies a number of intuitive desiderata, including: (1) it learns to predict patterns of truth and falsehood in logical statements, oft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03543","kind":"arxiv","version":5},"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/1609.03543/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1609.03543","created_at":"2026-07-05T01:57:35.629907+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.03543v5","created_at":"2026-07-05T01:57:35.629907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03543","created_at":"2026-07-05T01:57:35.629907+00:00"},{"alias_kind":"pith_short_12","alias_value":"REJG5FYRH6T2","created_at":"2026-07-05T01:57:35.629907+00:00"},{"alias_kind":"pith_short_16","alias_value":"REJG5FYRH6T2FU3A","created_at":"2026-07-05T01:57:35.629907+00:00"},{"alias_kind":"pith_short_8","alias_value":"REJG5FYR","created_at":"2026-07-05T01:57:35.629907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.08112","citing_title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M","json":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M.json","graph_json":"https://pith.science/api/pith-number/REJG5FYRH6T2FU3A2Q4SMJME4M/graph.json","events_json":"https://pith.science/api/pith-number/REJG5FYRH6T2FU3A2Q4SMJME4M/events.json","paper":"https://pith.science/paper/REJG5FYR"},"agent_actions":{"view_html":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M","download_json":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M.json","view_paper":"https://pith.science/paper/REJG5FYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.03543&json=true","fetch_graph":"https://pith.science/api/pith-number/REJG5FYRH6T2FU3A2Q4SMJME4M/graph.json","fetch_events":"https://pith.science/api/pith-number/REJG5FYRH6T2FU3A2Q4SMJME4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M/action/storage_attestation","attest_author":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M/action/author_attestation","sign_citation":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M/action/citation_signature","submit_replication":"https://pith.science/pith/REJG5FYRH6T2FU3A2Q4SMJME4M/action/replication_record"}},"created_at":"2026-07-05T01:57:35.629907+00:00","updated_at":"2026-07-05T01:57:35.629907+00:00"}