{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:766CQWYPDFLOP44HWOO76OFEVG","short_pith_number":"pith:766CQWYP","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"},"canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","source":{"kind":"arxiv","id":"2407.11004","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:766CQWYPDFLOP44HWOO76OFEVG","target":"record","payload":{"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"},"canonical_sha256":"ffbc285b0f1956e7f387b39dff38a4a9b67a6aabb8f34eb4565cba62c3768e1e","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"},"source_kind":"arxiv","source_id":"2407.11004","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zZrSl7Z9fjxPMvR/D/FiVGKEA6Wp7qp4Vp9jYhbyH87ExMqzEiDjGm9tgCTPdiAH5ciZKxJaI7SSzGfI096Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:02:38.368897Z"},"content_sha256":"1919b60801bdda0afb03b1c40095400347637296f08c87db04fe44fbe5d35dc8","schema_version":"1.0","event_id":"sha256:1919b60801bdda0afb03b1c40095400347637296f08c87db04fe44fbe5d35dc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:766CQWYPDFLOP44HWOO76OFEVG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydRyvMoTPM9jIJ/5QLpBFbdwuFm7rRIOBXr0s8nTO9ZNxxz+lQCWpE97t9BLJ0ol8qjIp6lnQ3zrXAZRNSzVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:02:38.369391Z"},"content_sha256":"38cd808936593f0cf87244e6381bab1d277bc1a07b36b3aaa34b4357706c2ce6","schema_version":"1.0","event_id":"sha256:38cd808936593f0cf87244e6381bab1d277bc1a07b36b3aaa34b4357706c2ce6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/bundle.json","state_url":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/766CQWYPDFLOP44HWOO76OFEVG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T06:02:38Z","links":{"resolver":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG","bundle":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/bundle.json","state":"https://pith.science/pith/766CQWYPDFLOP44HWOO76OFEVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/766CQWYPDFLOP44HWOO76OFEVG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"upxfOxWLDQshP56HJmkhuFCf/wb+DXc9+6h8XGy4j5rEN8iFMbsK/+Cnd7TSmT+Ws6NT4ELUIFyFDzw78Xm5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:02:38.373968Z","bundle_sha256":"54390cfea497f4e275014f79ade53bf065b510bff06ae4b153018e01acc098ee"}}