{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2001:DLOLEQDAQJO2RTDOXHZMV22AHP","short_pith_number":"pith:DLOLEQDA","schema_version":"1.0","canonical_sha256":"1adcb24060825da8cc6eb9f2caeb403be5ccebc4daff70e1baae7c8cadd0321b","source":{"kind":"arxiv","id":"cs/0101019","version":2},"attestation_state":"computed","paper":{"title":"General Loss Bounds for Universal Sequence Prediction","license":"","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.AI","authors_text":"Marcus Hutter","submitted_at":"2001-01-21T17:19:37Z","abstract_excerpt":"The Bayesian framework is ideally suited for induction problems. The probability of observing $x_t$ at time $t$, given past observations $x_1...x_{t-1}$ can be computed with Bayes' rule if the true distribution $\\mu$ of the sequences $x_1x_2x_3...$ is known. The problem, however, is that in many cases one does not even have a reasonable estimate of the true distribution. In order to overcome this problem a universal distribution $\\xi$ is defined as a weighted sum of distributions $\\mu_i\\inM$, where $M$ is any countable set of distributions including $\\mu$. This is a generalization of Solomonof"},"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":"cs/0101019","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.AI","submitted_at":"2001-01-21T17:19:37Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"71f2bf2e57bc48d8cb04296ab4de9a809b3f8d8683b6d2f04eeaa49b88221714","abstract_canon_sha256":"43b67548bd427d2c45bc330b535ee95a6d70872a9f3756fcd18c9bc46fed0bec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:08:54.389136Z","signature_b64":"OAnLD0xTjjYBiUBBqCsF997itVhgkemYaNaNmhJ0plYlQoRJmcsTQmrgHBo92t5xE3CWg3KcQZ+VHf38MH6qAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1adcb24060825da8cc6eb9f2caeb403be5ccebc4daff70e1baae7c8cadd0321b","last_reissued_at":"2026-05-18T04:08:54.388719Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:08:54.388719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General Loss Bounds for Universal Sequence Prediction","license":"","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.AI","authors_text":"Marcus Hutter","submitted_at":"2001-01-21T17:19:37Z","abstract_excerpt":"The Bayesian framework is ideally suited for induction problems. The probability of observing $x_t$ at time $t$, given past observations $x_1...x_{t-1}$ can be computed with Bayes' rule if the true distribution $\\mu$ of the sequences $x_1x_2x_3...$ is known. The problem, however, is that in many cases one does not even have a reasonable estimate of the true distribution. In order to overcome this problem a universal distribution $\\xi$ is defined as a weighted sum of distributions $\\mu_i\\inM$, where $M$ is any countable set of distributions including $\\mu$. This is a generalization of Solomonof"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0101019","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":""},"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":"cs/0101019","created_at":"2026-05-18T04:08:54.388781+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0101019v2","created_at":"2026-05-18T04:08:54.388781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0101019","created_at":"2026-05-18T04:08:54.388781+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLOLEQDAQJO2","created_at":"2026-05-18T12:25:50.254431+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLOLEQDAQJO2RTDO","created_at":"2026-05-18T12:25:50.254431+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLOLEQDA","created_at":"2026-05-18T12:25:50.254431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01005","citing_title":"Hierarchical Solomonoff Induction: An Unbounded Machine Learning Model","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP","json":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP.json","graph_json":"https://pith.science/api/pith-number/DLOLEQDAQJO2RTDOXHZMV22AHP/graph.json","events_json":"https://pith.science/api/pith-number/DLOLEQDAQJO2RTDOXHZMV22AHP/events.json","paper":"https://pith.science/paper/DLOLEQDA"},"agent_actions":{"view_html":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP","download_json":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP.json","view_paper":"https://pith.science/paper/DLOLEQDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0101019&json=true","fetch_graph":"https://pith.science/api/pith-number/DLOLEQDAQJO2RTDOXHZMV22AHP/graph.json","fetch_events":"https://pith.science/api/pith-number/DLOLEQDAQJO2RTDOXHZMV22AHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP/action/storage_attestation","attest_author":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP/action/author_attestation","sign_citation":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP/action/citation_signature","submit_replication":"https://pith.science/pith/DLOLEQDAQJO2RTDOXHZMV22AHP/action/replication_record"}},"created_at":"2026-05-18T04:08:54.388781+00:00","updated_at":"2026-05-18T04:08:54.388781+00:00"}