{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W6V6376T3EJNDV4FXFVS6IZOOO","short_pith_number":"pith:W6V6376T","canonical_record":{"source":{"id":"2306.15766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T19:29:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"527f93bd49d01d7593922b5c237c68c23c4ab1d07afe09c328a40a4c45bad3b8","abstract_canon_sha256":"3d4dbdbaa97517f3990fdf4474680714a0aaed94b89e8edff193a54ec2d1adbe"},"schema_version":"1.0"},"canonical_sha256":"b7abedffd3d912d1d785b96b2f232e73a43e0efd6041028f94260ea32d704fd8","source":{"kind":"arxiv","id":"2306.15766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15766","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15766v1","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15766","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"W6V6376T3EJN","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"W6V6376T3EJNDV4F","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"W6V6376T","created_at":"2026-07-05T06:25:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W6V6376T3EJNDV4FXFVS6IZOOO","target":"record","payload":{"canonical_record":{"source":{"id":"2306.15766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T19:29:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"527f93bd49d01d7593922b5c237c68c23c4ab1d07afe09c328a40a4c45bad3b8","abstract_canon_sha256":"3d4dbdbaa97517f3990fdf4474680714a0aaed94b89e8edff193a54ec2d1adbe"},"schema_version":"1.0"},"canonical_sha256":"b7abedffd3d912d1d785b96b2f232e73a43e0efd6041028f94260ea32d704fd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:44.182467Z","signature_b64":"lmoTnHdK/8g2YE6isR4RkcgrABnt08LRdeuLA4jK+MYKFCUiI8mUTeOFoTQ2ivYGrPp3dMo85TVkYun4RzDfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7abedffd3d912d1d785b96b2f232e73a43e0efd6041028f94260ea32d704fd8","last_reissued_at":"2026-07-05T06:25:44.181996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:44.181996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.15766","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9tywA6yuD4FUDyQU/GPRzYZENqSML0dQk7hOrO33zJVOw6KWlrvu2t1Kyz4zU5qSJMl1ne4asDaRnoeJhgIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:56:42.484521Z"},"content_sha256":"811c00b4dc509576c900648f40685d21f710296b8227e45044159015c30404f0","schema_version":"1.0","event_id":"sha256:811c00b4dc509576c900648f40685d21f710296b8227e45044159015c30404f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W6V6376T3EJNDV4FXFVS6IZOOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Sharma, Parikshit Bansal","submitted_at":"2023-06-27T19:29:55Z","abstract_excerpt":"State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth labels for the specific domain, we study the use of large language models (LLMs) for annotating inputs and improving the generalization of NLP models. Specifically, given a budget for LLM annotations, we present an algorithm for sampling the most informative inputs to annotate and retrain the NLP model. We find that popular active learning strategies such as un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15766","kind":"arxiv","version":1},"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/2306.15766/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":"2026-07-05T06:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xAxQ1NSLNiFZ6beG9H2OKErFlX2UEX1LIYdIK1dvt/lFwkZ5fCIzfY1/RY6/gpNJ/vRQ+JO1/XweBZNlNnYSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:56:42.485033Z"},"content_sha256":"e7eccda65c9ae6058e27d5f87935fee1a6f1ab02300d95b1f6c14dfe99db54b2","schema_version":"1.0","event_id":"sha256:e7eccda65c9ae6058e27d5f87935fee1a6f1ab02300d95b1f6c14dfe99db54b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6V6376T3EJNDV4FXFVS6IZOOO/bundle.json","state_url":"https://pith.science/pith/W6V6376T3EJNDV4FXFVS6IZOOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6V6376T3EJNDV4FXFVS6IZOOO/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":"2026-08-09T23:56:42Z","links":{"resolver":"https://pith.science/pith/W6V6376T3EJNDV4FXFVS6IZOOO","bundle":"https://pith.science/pith/W6V6376T3EJNDV4FXFVS6IZOOO/bundle.json","state":"https://pith.science/pith/W6V6376T3EJNDV4FXFVS6IZOOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6V6376T3EJNDV4FXFVS6IZOOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W6V6376T3EJNDV4FXFVS6IZOOO","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":"3d4dbdbaa97517f3990fdf4474680714a0aaed94b89e8edff193a54ec2d1adbe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T19:29:55Z","title_canon_sha256":"527f93bd49d01d7593922b5c237c68c23c4ab1d07afe09c328a40a4c45bad3b8"},"schema_version":"1.0","source":{"id":"2306.15766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15766","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15766v1","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15766","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"W6V6376T3EJN","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"W6V6376T3EJNDV4F","created_at":"2026-07-05T06:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"W6V6376T","created_at":"2026-07-05T06:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:e7eccda65c9ae6058e27d5f87935fee1a6f1ab02300d95b1f6c14dfe99db54b2","target":"graph","created_at":"2026-07-05T06:25:44Z","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/2306.15766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth labels for the specific domain, we study the use of large language models (LLMs) for annotating inputs and improving the generalization of NLP models. Specifically, given a budget for LLM annotations, we present an algorithm for sampling the most informative inputs to annotate and retrain the NLP model. We find that popular active learning strategies such as un","authors_text":"Amit Sharma, Parikshit Bansal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T19:29:55Z","title":"Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15766","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":"sha256:811c00b4dc509576c900648f40685d21f710296b8227e45044159015c30404f0","target":"record","created_at":"2026-07-05T06:25:44Z","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":"3d4dbdbaa97517f3990fdf4474680714a0aaed94b89e8edff193a54ec2d1adbe","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T19:29:55Z","title_canon_sha256":"527f93bd49d01d7593922b5c237c68c23c4ab1d07afe09c328a40a4c45bad3b8"},"schema_version":"1.0","source":{"id":"2306.15766","kind":"arxiv","version":1}},"canonical_sha256":"b7abedffd3d912d1d785b96b2f232e73a43e0efd6041028f94260ea32d704fd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7abedffd3d912d1d785b96b2f232e73a43e0efd6041028f94260ea32d704fd8","first_computed_at":"2026-07-05T06:25:44.181996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:44.181996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lmoTnHdK/8g2YE6isR4RkcgrABnt08LRdeuLA4jK+MYKFCUiI8mUTeOFoTQ2ivYGrPp3dMo85TVkYun4RzDfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:44.182467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:811c00b4dc509576c900648f40685d21f710296b8227e45044159015c30404f0","sha256:e7eccda65c9ae6058e27d5f87935fee1a6f1ab02300d95b1f6c14dfe99db54b2"],"state_sha256":"9fdba7fea99edbbf8c658471b8651a43d53ee75294d8f3135a3460333dc1add2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOKiGrjsAk8OPRd2Xi969EX7r4h1zqt2TcO6+kLN/HTJRNa6Qy681axhGi90YLUQSDV/VAbR+qNP0K2M1AsADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:56:42.489202Z","bundle_sha256":"db56d293f08d6114e3daa96d4e0c927659fbcbc0fab588524f81a32c66889333"}}