{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LZX2FD7BPEMI6NCJIN5HPT5HH4","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":"ca2ccfe656981d54a933bea019c6c8778c43fb2182f6694ae5170eb1d180e580","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T10:58:01Z","title_canon_sha256":"b77242462f75f1601aaf2df95c85770b14ad3f75634907c2fb9e1d4496bdef49"},"schema_version":"1.0","source":{"id":"2605.21515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21515","created_at":"2026-05-22T00:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21515v1","created_at":"2026-05-22T00:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21515","created_at":"2026-05-22T00:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"LZX2FD7BPEMI","created_at":"2026-05-22T00:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"LZX2FD7BPEMI6NCJ","created_at":"2026-05-22T00:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"LZX2FD7B","created_at":"2026-05-22T00:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:ad1dcc4922180222f8adf00753a98fadb3f98e7ba28de910c89e300bef4c3226","target":"graph","created_at":"2026-05-22T00:02:27Z","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/2605.21515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given a program, either symbolic (e.g. Python) or a prompt executed on an LLM, and a few in-domain examples, predict its performance on unseen tasks from the same domain. We use a simple coin-flip model, treating each pass/fail program execution as a Bernoulli random variable, whose success probability is the programs unknown performance. In this model, performance depends entirely on: 1) the observed execution outcomes o","authors_text":"Chengqi Zheng, Kevin Ellis, Keya Hu, Shuzhi Liu, Tao Wu, Yewen Pu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T10:58:01Z","title":"Predicting Performance of Symbolic and Prompt Programs with Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21515","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":"sha256:080c3a893cc205e7bdd2750e2c02d563bfb66413bdb0ebf5e758f3aab5191d91","target":"record","created_at":"2026-05-22T00:02:27Z","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":"ca2ccfe656981d54a933bea019c6c8778c43fb2182f6694ae5170eb1d180e580","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T10:58:01Z","title_canon_sha256":"b77242462f75f1601aaf2df95c85770b14ad3f75634907c2fb9e1d4496bdef49"},"schema_version":"1.0","source":{"id":"2605.21515","kind":"arxiv","version":1}},"canonical_sha256":"5e6fa28fe179188f3449437a77cfa73f163ef77b1151eaf3e479e03d27695844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e6fa28fe179188f3449437a77cfa73f163ef77b1151eaf3e479e03d27695844","first_computed_at":"2026-05-22T00:02:27.407677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T00:02:27.407677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FFy8URVvD+bE/Mo3h7fBkXLB2MC0DIkUYwJP73HuQfVznaCVxuKPCbN2fBTxz0dOcnmNKWgC79VfD2aR17DsAQ==","signature_status":"signed_v1","signed_at":"2026-05-22T00:02:27.408094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:080c3a893cc205e7bdd2750e2c02d563bfb66413bdb0ebf5e758f3aab5191d91","sha256:ad1dcc4922180222f8adf00753a98fadb3f98e7ba28de910c89e300bef4c3226"],"state_sha256":"35851897410d948a62664d9b9dfc57da0e6475c3fa16cfa66a9b089e0d541403"}