{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PAVMOPZIFSPLLDJTVVK3ULJES","short_pith_number":"pith:6PAVMOPZ","canonical_record":{"source":{"id":"2501.03892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-07T16:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"41b656b768fbb1d31610dfbd87ceb55dfa57ffab614d1e1b0d7804ab90ffbc3c","abstract_canon_sha256":"726b1ec24bbf2224264df954924e8577d2715760adb0903b468178865b337682"},"schema_version":"1.0"},"canonical_sha256":"f3c15639f94164f5ac699d6aadd16924b745e22e7f948d6aa71eadd67011a50f","source":{"kind":"arxiv","id":"2501.03892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03892","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03892v1","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03892","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"6PAVMOPZIFSP","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"6PAVMOPZIFSPLLDJ","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"6PAVMOPZ","created_at":"2026-07-05T09:58:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PAVMOPZIFSPLLDJTVVK3ULJES","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-07T16:00:40Z","cross_cats_sorted":[],"title_canon_sha256":"41b656b768fbb1d31610dfbd87ceb55dfa57ffab614d1e1b0d7804ab90ffbc3c","abstract_canon_sha256":"726b1ec24bbf2224264df954924e8577d2715760adb0903b468178865b337682"},"schema_version":"1.0"},"canonical_sha256":"f3c15639f94164f5ac699d6aadd16924b745e22e7f948d6aa71eadd67011a50f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:02.844009Z","signature_b64":"NyB3CxGY8mOxJeeavTMebBHiTV21KJafkKyppUXQbcfugqQnucDUd2hagWNa0kWSmQos1a1g4/cA7gO7Pv2fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c15639f94164f5ac699d6aadd16924b745e22e7f948d6aa71eadd67011a50f","last_reissued_at":"2026-07-05T09:58:02.843562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:02.843562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03892","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":"2026-07-05T09:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWvwDaLSVOJ+UqObUFz2tbIC0Sa1vXMdXFHDld5a74u3zOnGxdilYV+zw0va74427GVLdPpWdIza0Nl+NVyKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:11.041298Z"},"content_sha256":"6703b857e4afe7d9e25169945b306154cd22c7450e9069f2ded4227df12131c3","schema_version":"1.0","event_id":"sha256:6703b857e4afe7d9e25169945b306154cd22c7450e9069f2ded4227df12131c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PAVMOPZIFSPLLDJTVVK3ULJES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Austin Peters, Chuxuan Hu, Daniel Kang","submitted_at":"2025-01-07T16:00:40Z","abstract_excerpt":"Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not natively present. Performing this analysis in a cost-efficient manner requires using machine learning (ML) models to extract the semantic information and subsequently analyze the now structured data. However, this process remains challenging for domain experts.\n  To demonstrate the challenges in social science analytics, we collect a dataset, QUIET-ML, of 120 real-world social science queries in natural language and their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03892","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/2501.03892/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":"2026-07-05T09:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4loHqk+oT5LkjOGF+v8mog4KyC7ijVGeww3qgb/WYIVVVOZ0Shos8dvMaOlHfoq+nCYYgPtzxzjVgJh7HYoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:11.041819Z"},"content_sha256":"c0c2d454eba834d4709c237145d760e19b649afbf02632c2971cf02598984ef9","schema_version":"1.0","event_id":"sha256:c0c2d454eba834d4709c237145d760e19b649afbf02632c2971cf02598984ef9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/bundle.json","state_url":"https://pith.science/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/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":"2026-08-11T13:04:11Z","links":{"resolver":"https://pith.science/pith/6PAVMOPZIFSPLLDJTVVK3ULJES","bundle":"https://pith.science/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/bundle.json","state":"https://pith.science/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PAVMOPZIFSPLLDJTVVK3ULJES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PAVMOPZIFSPLLDJTVVK3ULJES","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":"726b1ec24bbf2224264df954924e8577d2715760adb0903b468178865b337682","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-07T16:00:40Z","title_canon_sha256":"41b656b768fbb1d31610dfbd87ceb55dfa57ffab614d1e1b0d7804ab90ffbc3c"},"schema_version":"1.0","source":{"id":"2501.03892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03892","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03892v1","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03892","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"6PAVMOPZIFSP","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"6PAVMOPZIFSPLLDJ","created_at":"2026-07-05T09:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"6PAVMOPZ","created_at":"2026-07-05T09:58:02Z"}],"graph_snapshots":[{"event_id":"sha256:c0c2d454eba834d4709c237145d760e19b649afbf02632c2971cf02598984ef9","target":"graph","created_at":"2026-07-05T09:58:02Z","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/2501.03892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not natively present. Performing this analysis in a cost-efficient manner requires using machine learning (ML) models to extract the semantic information and subsequently analyze the now structured data. However, this process remains challenging for domain experts.\n  To demonstrate the challenges in social science analytics, we collect a dataset, QUIET-ML, of 120 real-world social science queries in natural language and their","authors_text":"Austin Peters, Chuxuan Hu, Daniel Kang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-07T16:00:40Z","title":"LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03892","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":"sha256:6703b857e4afe7d9e25169945b306154cd22c7450e9069f2ded4227df12131c3","target":"record","created_at":"2026-07-05T09:58:02Z","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":"726b1ec24bbf2224264df954924e8577d2715760adb0903b468178865b337682","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-07T16:00:40Z","title_canon_sha256":"41b656b768fbb1d31610dfbd87ceb55dfa57ffab614d1e1b0d7804ab90ffbc3c"},"schema_version":"1.0","source":{"id":"2501.03892","kind":"arxiv","version":1}},"canonical_sha256":"f3c15639f94164f5ac699d6aadd16924b745e22e7f948d6aa71eadd67011a50f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c15639f94164f5ac699d6aadd16924b745e22e7f948d6aa71eadd67011a50f","first_computed_at":"2026-07-05T09:58:02.843562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:02.843562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NyB3CxGY8mOxJeeavTMebBHiTV21KJafkKyppUXQbcfugqQnucDUd2hagWNa0kWSmQos1a1g4/cA7gO7Pv2fDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:02.844009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6703b857e4afe7d9e25169945b306154cd22c7450e9069f2ded4227df12131c3","sha256:c0c2d454eba834d4709c237145d760e19b649afbf02632c2971cf02598984ef9"],"state_sha256":"322cec29bab940c8cbe243951f938deffd8247643433b8f95c7a26091a820716"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+9IzhLRfdG719KHeH4PwRaqPCYnjlXQs8NmPnF+FjN0X0Q4ditHn2ZL6jwAKppV7CjxaAspcKvaDfbGsNa2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:04:11.046689Z","bundle_sha256":"09cd15c486dbf694334c38991a3f351cb8966dccc054ebb4cf1ffe17b394764b"}}