{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FBI3FJW3Q6YUXNEUY6HX6SMZKV","short_pith_number":"pith:FBI3FJW3","schema_version":"1.0","canonical_sha256":"2851b2a6db87b14bb494c78f7f49995558e63e525bcc40b8e04f7defd453b476","source":{"kind":"arxiv","id":"2504.00847","version":2},"attestation_state":"computed","paper":{"title":"From learnable objects to learnable random objects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.LO"],"primary_cat":"cs.LO","authors_text":"Aaron Anderson, Michael Benedikt","submitted_at":"2025-04-01T14:34:54Z","abstract_excerpt":"We consider the relationship between learnability of a \"base class\" of functions on a set $X$, and learnability of a class of statistical functions derived from the base class. For example, we refine results showing that learnability of a family $h_p: p \\in Y$ of functions implies learnability of the family of functions $h_\\mu=\\lambda p: Y. E_\\mu(h_p)$, where $E_\\mu$ is the expectation with respect to $\\mu$, and $\\mu$ ranges over probability distributions on $X$. We will look at both Probably Approximately Correct (PAC) learning, where example inputs and outputs are chosen at random, and onlin"},"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":"2504.00847","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LO","submitted_at":"2025-04-01T14:34:54Z","cross_cats_sorted":["cs.LG","math.LO"],"title_canon_sha256":"22d02d8c15e13f8f8a7ff2d9036a4ed56aa275cc6ab6570c8ae53199b09ce22b","abstract_canon_sha256":"93e42f7c5c0b15e86b3c353216af0c07c3edfaccef88c56c90438965a1a31872"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:06.959043Z","signature_b64":"Rd+CIJF1lZr7EmecxHQtUBH7241YVEGkVbYo6QS7KgF4h2uRZcXBDsF0SWZLm3C25byGyEdHWv6njxjWWCxDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2851b2a6db87b14bb494c78f7f49995558e63e525bcc40b8e04f7defd453b476","last_reissued_at":"2026-07-05T11:10:06.958549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:06.958549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From learnable objects to learnable random objects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.LO"],"primary_cat":"cs.LO","authors_text":"Aaron Anderson, Michael Benedikt","submitted_at":"2025-04-01T14:34:54Z","abstract_excerpt":"We consider the relationship between learnability of a \"base class\" of functions on a set $X$, and learnability of a class of statistical functions derived from the base class. For example, we refine results showing that learnability of a family $h_p: p \\in Y$ of functions implies learnability of the family of functions $h_\\mu=\\lambda p: Y. E_\\mu(h_p)$, where $E_\\mu$ is the expectation with respect to $\\mu$, and $\\mu$ ranges over probability distributions on $X$. We will look at both Probably Approximately Correct (PAC) learning, where example inputs and outputs are chosen at random, and onlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00847","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.00847/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":"2504.00847","created_at":"2026-07-05T11:10:06.958607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00847v2","created_at":"2026-07-05T11:10:06.958607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00847","created_at":"2026-07-05T11:10:06.958607+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBI3FJW3Q6YU","created_at":"2026-07-05T11:10:06.958607+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBI3FJW3Q6YUXNEU","created_at":"2026-07-05T11:10:06.958607+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBI3FJW3","created_at":"2026-07-05T11:10:06.958607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01107","citing_title":"How (and when) can you fit examples to logic-based hypothesis classes over infinite structures?","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV","json":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV.json","graph_json":"https://pith.science/api/pith-number/FBI3FJW3Q6YUXNEUY6HX6SMZKV/graph.json","events_json":"https://pith.science/api/pith-number/FBI3FJW3Q6YUXNEUY6HX6SMZKV/events.json","paper":"https://pith.science/paper/FBI3FJW3"},"agent_actions":{"view_html":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV","download_json":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV.json","view_paper":"https://pith.science/paper/FBI3FJW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00847&json=true","fetch_graph":"https://pith.science/api/pith-number/FBI3FJW3Q6YUXNEUY6HX6SMZKV/graph.json","fetch_events":"https://pith.science/api/pith-number/FBI3FJW3Q6YUXNEUY6HX6SMZKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV/action/storage_attestation","attest_author":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV/action/author_attestation","sign_citation":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV/action/citation_signature","submit_replication":"https://pith.science/pith/FBI3FJW3Q6YUXNEUY6HX6SMZKV/action/replication_record"}},"created_at":"2026-07-05T11:10:06.958607+00:00","updated_at":"2026-07-05T11:10:06.958607+00:00"}