{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ENMAAZQAR6R4ME2Y7GXDUU63T6","short_pith_number":"pith:ENMAAZQA","schema_version":"1.0","canonical_sha256":"23580066008fa3c61358f9ae3a53db9f9b2d3ac1ac3136b080be256cca343967","source":{"kind":"arxiv","id":"2103.05030","version":4},"attestation_state":"computed","paper":{"title":"Program Synthesis Over Noisy Data with Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PL","authors_text":"Martin Rinard, Shivam Handa","submitted_at":"2021-03-08T19:39:13Z","abstract_excerpt":"We explore and formalize the task of synthesizing programs over noisy data, i.e., data that may contain corrupted input-output examples. By formalizing the concept of a Noise Source, an Input Source, and a prior distribution over programs, we formalize the probabilistic process which constructs a noisy dataset. This formalism allows us to define the correctness of a synthesis algorithm, in terms of its ability to synthesize the hidden underlying program. The probability of a synthesis algorithm being correct depends upon the match between the Noise Source and the Loss Function used in the synt"},"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":"2103.05030","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2021-03-08T19:39:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"56635e06d0f6f4c348a5bcfbf6fb5be1de68560ab977b1cf19cd41bf09bdd4e3","abstract_canon_sha256":"a9d49426c2b59b338d051e9f117263d5c3eaf17cda566f887f4ba746f8f1a1c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:53.549569Z","signature_b64":"l37OylGQ1nWQ0AgyoHmr7y7yMN/vuboVqUIALLbrg1TBTCVI0I1+ipOFA9W/siGMgpqbLX2pg23Oi346uZ/fBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23580066008fa3c61358f9ae3a53db9f9b2d3ac1ac3136b080be256cca343967","last_reissued_at":"2026-07-05T02:35:53.549119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:53.549119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Program Synthesis Over Noisy Data with Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PL","authors_text":"Martin Rinard, Shivam Handa","submitted_at":"2021-03-08T19:39:13Z","abstract_excerpt":"We explore and formalize the task of synthesizing programs over noisy data, i.e., data that may contain corrupted input-output examples. By formalizing the concept of a Noise Source, an Input Source, and a prior distribution over programs, we formalize the probabilistic process which constructs a noisy dataset. This formalism allows us to define the correctness of a synthesis algorithm, in terms of its ability to synthesize the hidden underlying program. The probability of a synthesis algorithm being correct depends upon the match between the Noise Source and the Loss Function used in the synt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05030","kind":"arxiv","version":4},"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/2103.05030/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":"2103.05030","created_at":"2026-07-05T02:35:53.549182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05030v4","created_at":"2026-07-05T02:35:53.549182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05030","created_at":"2026-07-05T02:35:53.549182+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENMAAZQAR6R4","created_at":"2026-07-05T02:35:53.549182+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENMAAZQAR6R4ME2Y","created_at":"2026-07-05T02:35:53.549182+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENMAAZQA","created_at":"2026-07-05T02:35:53.549182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01280","citing_title":"Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6","json":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6.json","graph_json":"https://pith.science/api/pith-number/ENMAAZQAR6R4ME2Y7GXDUU63T6/graph.json","events_json":"https://pith.science/api/pith-number/ENMAAZQAR6R4ME2Y7GXDUU63T6/events.json","paper":"https://pith.science/paper/ENMAAZQA"},"agent_actions":{"view_html":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6","download_json":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6.json","view_paper":"https://pith.science/paper/ENMAAZQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05030&json=true","fetch_graph":"https://pith.science/api/pith-number/ENMAAZQAR6R4ME2Y7GXDUU63T6/graph.json","fetch_events":"https://pith.science/api/pith-number/ENMAAZQAR6R4ME2Y7GXDUU63T6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6/action/storage_attestation","attest_author":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6/action/author_attestation","sign_citation":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6/action/citation_signature","submit_replication":"https://pith.science/pith/ENMAAZQAR6R4ME2Y7GXDUU63T6/action/replication_record"}},"created_at":"2026-07-05T02:35:53.549182+00:00","updated_at":"2026-07-05T02:35:53.549182+00:00"}