{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZSQWKHX3SZAPAZAZVCWG2UKU4D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ede4c56b8fb20ae65642321e48edf1abc22de44e46d2f40cbc371ad6855ef44","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2023-09-21T01:59:20Z","title_canon_sha256":"4b326ee9df3d490c3c9e972f1dd09af80456a46e8a0676bad9ebe80dea0fb600"},"schema_version":"1.0","source":{"id":"2309.11726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11726","created_at":"2026-07-05T06:52:53Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11726v1","created_at":"2026-07-05T06:52:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11726","created_at":"2026-07-05T06:52:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZSQWKHX3SZAP","created_at":"2026-07-05T06:52:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZSQWKHX3SZAPAZAZ","created_at":"2026-07-05T06:52:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZSQWKHX3","created_at":"2026-07-05T06:52:53Z"}],"graph_snapshots":[{"event_id":"sha256:037a9ccccd71699c0f3ac314c4918c4a71ad4c5df05e8ff5e0974419676136b9","target":"graph","created_at":"2026-07-05T06:52:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.11726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Programmers and researchers are increasingly developing surrogates of programs, models of a subset of the observable behavior of a given program, to solve a variety of software development challenges. Programmers train surrogates from measurements of the behavior of a program on a dataset of input examples. A key challenge of surrogate construction is determining what training data to use to train a surrogate of a given program.\n  We present a methodology for sampling datasets to train neural-network-based surrogates of programs. We first characterize the proportion of data to sample from each","authors_text":"Alex Renda, Michael Carbin, Yi Ding","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2023-09-21T01:59:20Z","title":"Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11726","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb1627330fc9b9cabe210c0308ab1d6f1b13507d74860cd42ef4238df846eb29","target":"record","created_at":"2026-07-05T06:52:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ede4c56b8fb20ae65642321e48edf1abc22de44e46d2f40cbc371ad6855ef44","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2023-09-21T01:59:20Z","title_canon_sha256":"4b326ee9df3d490c3c9e972f1dd09af80456a46e8a0676bad9ebe80dea0fb600"},"schema_version":"1.0","source":{"id":"2309.11726","kind":"arxiv","version":1}},"canonical_sha256":"cca1651efb9640f06419a8ac6d5154e0ff69ce2bda9c77019ea774ce3cc3297b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cca1651efb9640f06419a8ac6d5154e0ff69ce2bda9c77019ea774ce3cc3297b","first_computed_at":"2026-07-05T06:52:53.660172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:53.660172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2HQsZdsnWpjoZhQUbFk9DD9dw6hRSOn/2lD3GanPVADSkoUZlscLnpY01c/NjHfBrHfIeU4MidulQSaOYCD6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:53.660654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb1627330fc9b9cabe210c0308ab1d6f1b13507d74860cd42ef4238df846eb29","sha256:037a9ccccd71699c0f3ac314c4918c4a71ad4c5df05e8ff5e0974419676136b9"],"state_sha256":"d46935a0989a027a13fc44c2ba88e76ab060f69eaa9fed6022827e989587a180"}