{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SKQZVBCK572IH6L2PU2BE77DG5","short_pith_number":"pith:SKQZVBCK","canonical_record":{"source":{"id":"2403.18152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T23:32:52Z","cross_cats_sorted":[],"title_canon_sha256":"537a4ac75e885487eccd586d261ec6e99d54eea4bf7199a58ff3a0325c7b30c7","abstract_canon_sha256":"106574cf0e17243f86554f878a02eb4efee81aebad3ed0cefde70f61adc4b187"},"schema_version":"1.0"},"canonical_sha256":"92a19a844aeff483f97a7d34127fe3375184e031256ee59b742f08359cbc3e19","source":{"kind":"arxiv","id":"2403.18152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18152","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18152v1","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18152","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_12","alias_value":"SKQZVBCK572I","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_16","alias_value":"SKQZVBCK572IH6L2","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_8","alias_value":"SKQZVBCK","created_at":"2026-07-05T08:01:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SKQZVBCK572IH6L2PU2BE77DG5","target":"record","payload":{"canonical_record":{"source":{"id":"2403.18152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T23:32:52Z","cross_cats_sorted":[],"title_canon_sha256":"537a4ac75e885487eccd586d261ec6e99d54eea4bf7199a58ff3a0325c7b30c7","abstract_canon_sha256":"106574cf0e17243f86554f878a02eb4efee81aebad3ed0cefde70f61adc4b187"},"schema_version":"1.0"},"canonical_sha256":"92a19a844aeff483f97a7d34127fe3375184e031256ee59b742f08359cbc3e19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:05.441373Z","signature_b64":"+iYlbzQz0LCJ36XYccGXOkKjRxWLecA8NVxdwjtg6WIxncwszYgtLFdNwZNeuaw/14UZtYTfS1eSedzL/MRNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92a19a844aeff483f97a7d34127fe3375184e031256ee59b742f08359cbc3e19","last_reissued_at":"2026-07-05T08:01:05.440877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:05.440877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.18152","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":"2026-07-05T08:01:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUeSKIW/Gx7wia9zelJJgbyJNn+nUY/EhybzXNr5ViIniOirZfgJDsIzSCc39cLKN4ozE3fhHaovTIzj0kiUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:42:13.731245Z"},"content_sha256":"0dd916f7c48cf62c9b0a7f5803ecb94b352cee66362ce1fdd44b1b324aabc44d","schema_version":"1.0","event_id":"sha256:0dd916f7c48cf62c9b0a7f5803ecb94b352cee66362ce1fdd44b1b324aabc44d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SKQZVBCK572IH6L2PU2BE77DG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charese Smiley, Dongsheng Wang, Elena Kochkina, Sameena Shah, Simerjot Kaur, Suchetha Siddagangappa, Toyin Aguda","submitted_at":"2024-03-26T23:32:52Z","abstract_excerpt":"Collecting labeled datasets in finance is challenging due to scarcity of domain experts and higher cost of employing them. While Large Language Models (LLMs) have demonstrated remarkable performance in data annotation tasks on general domain datasets, their effectiveness on domain specific datasets remains underexplored. To address this gap, we investigate the potential of LLMs as efficient data annotators for extracting relations in financial documents. We compare the annotations produced by three LLMs (GPT-4, PaLM 2, and MPT Instruct) against expert annotators and crowdworkers. We demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18152","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/2403.18152/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":"2026-07-05T08:01:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eV9yPnkguwRQ5rrl24IecwKhnhnsubn8BWC8Bekq3Iwi9in9ukTcugba6IxLRMe27Plj+ovUm+npUydzaesFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:42:13.734512Z"},"content_sha256":"04266a4eb4640849249b4357205553f3398f9990fbdd6bb2ece50dc4cf737d19","schema_version":"1.0","event_id":"sha256:04266a4eb4640849249b4357205553f3398f9990fbdd6bb2ece50dc4cf737d19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKQZVBCK572IH6L2PU2BE77DG5/bundle.json","state_url":"https://pith.science/pith/SKQZVBCK572IH6L2PU2BE77DG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKQZVBCK572IH6L2PU2BE77DG5/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":"2026-08-13T18:42:13Z","links":{"resolver":"https://pith.science/pith/SKQZVBCK572IH6L2PU2BE77DG5","bundle":"https://pith.science/pith/SKQZVBCK572IH6L2PU2BE77DG5/bundle.json","state":"https://pith.science/pith/SKQZVBCK572IH6L2PU2BE77DG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKQZVBCK572IH6L2PU2BE77DG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SKQZVBCK572IH6L2PU2BE77DG5","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":"106574cf0e17243f86554f878a02eb4efee81aebad3ed0cefde70f61adc4b187","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T23:32:52Z","title_canon_sha256":"537a4ac75e885487eccd586d261ec6e99d54eea4bf7199a58ff3a0325c7b30c7"},"schema_version":"1.0","source":{"id":"2403.18152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18152","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18152v1","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18152","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_12","alias_value":"SKQZVBCK572I","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_16","alias_value":"SKQZVBCK572IH6L2","created_at":"2026-07-05T08:01:05Z"},{"alias_kind":"pith_short_8","alias_value":"SKQZVBCK","created_at":"2026-07-05T08:01:05Z"}],"graph_snapshots":[{"event_id":"sha256:04266a4eb4640849249b4357205553f3398f9990fbdd6bb2ece50dc4cf737d19","target":"graph","created_at":"2026-07-05T08:01:05Z","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/2403.18152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collecting labeled datasets in finance is challenging due to scarcity of domain experts and higher cost of employing them. While Large Language Models (LLMs) have demonstrated remarkable performance in data annotation tasks on general domain datasets, their effectiveness on domain specific datasets remains underexplored. To address this gap, we investigate the potential of LLMs as efficient data annotators for extracting relations in financial documents. We compare the annotations produced by three LLMs (GPT-4, PaLM 2, and MPT Instruct) against expert annotators and crowdworkers. We demonstrat","authors_text":"Charese Smiley, Dongsheng Wang, Elena Kochkina, Sameena Shah, Simerjot Kaur, Suchetha Siddagangappa, Toyin Aguda","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T23:32:52Z","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18152","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":"sha256:0dd916f7c48cf62c9b0a7f5803ecb94b352cee66362ce1fdd44b1b324aabc44d","target":"record","created_at":"2026-07-05T08:01:05Z","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":"106574cf0e17243f86554f878a02eb4efee81aebad3ed0cefde70f61adc4b187","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T23:32:52Z","title_canon_sha256":"537a4ac75e885487eccd586d261ec6e99d54eea4bf7199a58ff3a0325c7b30c7"},"schema_version":"1.0","source":{"id":"2403.18152","kind":"arxiv","version":1}},"canonical_sha256":"92a19a844aeff483f97a7d34127fe3375184e031256ee59b742f08359cbc3e19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92a19a844aeff483f97a7d34127fe3375184e031256ee59b742f08359cbc3e19","first_computed_at":"2026-07-05T08:01:05.440877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:05.440877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+iYlbzQz0LCJ36XYccGXOkKjRxWLecA8NVxdwjtg6WIxncwszYgtLFdNwZNeuaw/14UZtYTfS1eSedzL/MRNAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:05.441373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dd916f7c48cf62c9b0a7f5803ecb94b352cee66362ce1fdd44b1b324aabc44d","sha256:04266a4eb4640849249b4357205553f3398f9990fbdd6bb2ece50dc4cf737d19"],"state_sha256":"e9dce50133f6d97163acc71bfc729f7cdc858f122f334cda38f0e05ecfaa86f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1cC6oxgSuNdvUMckIeompb9Kzm6OBb+ltdm+v8pwZx4dlpPL/ckRSta6r02MPcKGkWTtTmoFvXcasHXm2C5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:42:13.813044Z","bundle_sha256":"b08cbcd2b6e4dda5d7f2945ae3622268983f3ff4631d5ed66b896985a0ec1394"}}