{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:766CQWYPDFLOP44HWOO76OFEVG","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":"3a734da97f710620b41ba533a17c9003d76e9704414de906aa53219d57f0cf2c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:58:26Z","title_canon_sha256":"814e03822372d8ef961acf5b99df3df62e821768fc9ddcd2627c8c255c04f068"},"schema_version":"1.0","source":{"id":"2407.11004","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11004","created_at":"2026-07-05T10:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11004v2","created_at":"2026-07-05T10:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11004","created_at":"2026-07-05T10:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"766CQWYPDFLO","created_at":"2026-07-05T10:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"766CQWYPDFLOP44H","created_at":"2026-07-05T10:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"766CQWYP","created_at":"2026-07-05T10:08:53Z"}],"graph_snapshots":[{"event_id":"sha256:38cd808936593f0cf87244e6381bab1d277bc1a07b36b3aaa34b4357706c2ce6","target":"graph","created_at":"2026-07-05T10:08:53Z","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/2407.11004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained models can be used as annotators, helping replace or augment crowdworkers and enabling distilling generalist models into smaller specialist models. Unfortunately, this comes at a cost: employing top-of-the-line models often requires paying thousands of dollars for API calls, while the resulting datasets are static and challenging to audit. To address these challenges, we propose a simple alternative: rather than directly querying labels from pretrained models, we task models to generate programs that can produce labels. These programs can be stored and applied locally, re-used","authors_text":"Catherine Cao, Frederic Sala, Tzu-Heng Huang, Vaishnavi Bhargava","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:58:26Z","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11004","kind":"arxiv","version":2},"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":"sha256:1919b60801bdda0afb03b1c40095400347637296f08c87db04fe44fbe5d35dc8","target":"record","created_at":"2026-07-05T10:08:53Z","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":"3a734da97f710620b41ba533a17c9003d76e9704414de906aa53219d57f0cf2c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:58:26Z","title_canon_sha256":"814e03822372d8ef961acf5b99df3df62e821768fc9ddcd2627c8c255c04f068"},"schema_version":"1.0","source":{"id":"2407.11004","kind":"arxiv","version":2}},"canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","first_computed_at":"2026-07-05T10:08:53.102246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:53.102246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8rAJH4eyjN5GaZeAjBTi41K3HuD2diuOsMw1aORFd2bfmkPsyKmA7A4Hooit54/je2iFE8PGKssDgeSRWv8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:53.102738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11004","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1919b60801bdda0afb03b1c40095400347637296f08c87db04fe44fbe5d35dc8","sha256:38cd808936593f0cf87244e6381bab1d277bc1a07b36b3aaa34b4357706c2ce6"],"state_sha256":"8ee8b5d7e9c467ee6addf9dc8ea884ecd89163583c372ca1bd12f89d583eae8f"}