{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:766CQWYPDFLOP44HWOO76OFEVG","short_pith_number":"pith:766CQWYP","schema_version":"1.0","canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","source":{"kind":"arxiv","id":"2407.11004","version":2},"attestation_state":"computed","paper":{"title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Catherine Cao, Frederic Sala, Tzu-Heng Huang, Vaishnavi Bhargava","submitted_at":"2024-06-25T17:58:26Z","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"},"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":"2407.11004","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:58:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"814e03822372d8ef961acf5b99df3df62e821768fc9ddcd2627c8c255c04f068","abstract_canon_sha256":"3a734da97f710620b41ba533a17c9003d76e9704414de906aa53219d57f0cf2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:53.102738Z","signature_b64":"r8rAJH4eyjN5GaZeAjBTi41K3HuD2diuOsMw1aORFd2bfmkPsyKmA7A4Hooit54/je2iFE8PGKssDgeSRWv8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","last_reissued_at":"2026-07-05T10:08:53.102246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:53.102246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Catherine Cao, Frederic Sala, Tzu-Heng Huang, Vaishnavi Bhargava","submitted_at":"2024-06-25T17:58:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11004","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/2407.11004/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":"2407.11004","created_at":"2026-07-05T10:08:53.102302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11004v2","created_at":"2026-07-05T10:08:53.102302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11004","created_at":"2026-07-05T10:08:53.102302+00:00"},{"alias_kind":"pith_short_12","alias_value":"766CQWYPDFLO","created_at":"2026-07-05T10:08:53.102302+00:00"},{"alias_kind":"pith_short_16","alias_value":"766CQWYPDFLOP44H","created_at":"2026-07-05T10:08:53.102302+00:00"},{"alias_kind":"pith_short_8","alias_value":"766CQWYP","created_at":"2026-07-05T10:08:53.102302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07727","citing_title":"Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG","json":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG.json","graph_json":"https://pith.science/api/pith-number/766CQWYPDFLOP44HWOO76OFEVG/graph.json","events_json":"https://pith.science/api/pith-number/766CQWYPDFLOP44HWOO76OFEVG/events.json","paper":"https://pith.science/paper/766CQWYP"},"agent_actions":{"view_html":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG","download_json":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG.json","view_paper":"https://pith.science/paper/766CQWYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11004&json=true","fetch_graph":"https://pith.science/api/pith-number/766CQWYPDFLOP44HWOO76OFEVG/graph.json","fetch_events":"https://pith.science/api/pith-number/766CQWYPDFLOP44HWOO76OFEVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/action/storage_attestation","attest_author":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/action/author_attestation","sign_citation":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/action/citation_signature","submit_replication":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/action/replication_record"}},"created_at":"2026-07-05T10:08:53.102302+00:00","updated_at":"2026-07-05T10:08:53.102302+00:00"}