{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ERKMLBY6RHGUGHFVI5LEI7SLKZ","short_pith_number":"pith:ERKMLBY6","canonical_record":{"source":{"id":"2411.19689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T13:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"d870bcc4c32abd3c0a28cfb54423c9de11f22a760294762d5ddd1483462b8cdb","abstract_canon_sha256":"557e287786628c8cd79b0db7f43ac0ea70a95fe0488056210bf5f43c0388e140"},"schema_version":"1.0"},"canonical_sha256":"2454c5871e89cd431cb54756447e4b56724786e037c3ad72b429d869e4aabb65","source":{"kind":"arxiv","id":"2411.19689","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19689","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19689v1","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19689","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"ERKMLBY6RHGU","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"ERKMLBY6RHGUGHFV","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"ERKMLBY6","created_at":"2026-07-05T09:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ERKMLBY6RHGUGHFVI5LEI7SLKZ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T13:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"d870bcc4c32abd3c0a28cfb54423c9de11f22a760294762d5ddd1483462b8cdb","abstract_canon_sha256":"557e287786628c8cd79b0db7f43ac0ea70a95fe0488056210bf5f43c0388e140"},"schema_version":"1.0"},"canonical_sha256":"2454c5871e89cd431cb54756447e4b56724786e037c3ad72b429d869e4aabb65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:06.680046Z","signature_b64":"nI734kzysGKqKPNp16ut0LJlOqK4aDURfqbZLZPvnS+3VXEXLIOILlrIxY85ZgWuUZxV0aLtVMF8Bhl8dKbsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2454c5871e89cd431cb54756447e4b56724786e037c3ad72b429d869e4aabb65","last_reissued_at":"2026-07-05T09:42:06.679533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:06.679533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19689","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":"2026-07-05T09:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4d1Sjg594aef4cQv/5tPc55QR/SXJpyutH/bz+3fBBLDxVNCtCwtTFx6G4sXaYrQ/hcthG9BQkbZnfviWT9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:08:32.473137Z"},"content_sha256":"eeeab7555a625b51af21c7549b1a5e18058fc503ff70893c6494b54683590e51","schema_version":"1.0","event_id":"sha256:eeeab7555a625b51af21c7549b1a5e18058fc503ff70893c6494b54683590e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ERKMLBY6RHGUGHFVI5LEI7SLKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anton Poletaev, John Francis, Jonathan Bright, Saba Esnaashari, Sukankana Chakraborty, Youmna Hashem","submitted_at":"2024-11-29T13:24:10Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in text analysis tasks, yet their evaluation on complex, real-world applications remains challenging. We define a set of tasks, Multi-Insight Multi-Document Extraction (MIMDE) tasks, which involves extracting an optimal set of insights from a document corpus and mapping these insights back to their source documents. This task is fundamental to many practical applications, from analyzing survey responses to processing medical records, where identifying and tracing key insights across documents is crucial. We develop an evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19689","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/2411.19689/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":"2026-07-05T09:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IRj+LMInIEzxM87r5ona9Ch2K2JFfe+WY3cfxqjx2RkT2gQQ/XQFFxrsX6WQ9zgkSKnO3WZs9RoOtwFbYW8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:08:32.473652Z"},"content_sha256":"318519b76a543dc2ca471d8fb1a9af26c929e29ffb556bb059eff8b4d6adfeeb","schema_version":"1.0","event_id":"sha256:318519b76a543dc2ca471d8fb1a9af26c929e29ffb556bb059eff8b4d6adfeeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/bundle.json","state_url":"https://pith.science/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/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":"2026-08-15T10:08:32Z","links":{"resolver":"https://pith.science/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ","bundle":"https://pith.science/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/bundle.json","state":"https://pith.science/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERKMLBY6RHGUGHFVI5LEI7SLKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ERKMLBY6RHGUGHFVI5LEI7SLKZ","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":"557e287786628c8cd79b0db7f43ac0ea70a95fe0488056210bf5f43c0388e140","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T13:24:10Z","title_canon_sha256":"d870bcc4c32abd3c0a28cfb54423c9de11f22a760294762d5ddd1483462b8cdb"},"schema_version":"1.0","source":{"id":"2411.19689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19689","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19689v1","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19689","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"ERKMLBY6RHGU","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"ERKMLBY6RHGUGHFV","created_at":"2026-07-05T09:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"ERKMLBY6","created_at":"2026-07-05T09:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:318519b76a543dc2ca471d8fb1a9af26c929e29ffb556bb059eff8b4d6adfeeb","target":"graph","created_at":"2026-07-05T09:42:06Z","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/2411.19689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in text analysis tasks, yet their evaluation on complex, real-world applications remains challenging. We define a set of tasks, Multi-Insight Multi-Document Extraction (MIMDE) tasks, which involves extracting an optimal set of insights from a document corpus and mapping these insights back to their source documents. This task is fundamental to many practical applications, from analyzing survey responses to processing medical records, where identifying and tracing key insights across documents is crucial. We develop an evalu","authors_text":"Anton Poletaev, John Francis, Jonathan Bright, Saba Esnaashari, Sukankana Chakraborty, Youmna Hashem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T13:24:10Z","title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19689","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:eeeab7555a625b51af21c7549b1a5e18058fc503ff70893c6494b54683590e51","target":"record","created_at":"2026-07-05T09:42:06Z","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":"557e287786628c8cd79b0db7f43ac0ea70a95fe0488056210bf5f43c0388e140","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T13:24:10Z","title_canon_sha256":"d870bcc4c32abd3c0a28cfb54423c9de11f22a760294762d5ddd1483462b8cdb"},"schema_version":"1.0","source":{"id":"2411.19689","kind":"arxiv","version":1}},"canonical_sha256":"2454c5871e89cd431cb54756447e4b56724786e037c3ad72b429d869e4aabb65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2454c5871e89cd431cb54756447e4b56724786e037c3ad72b429d869e4aabb65","first_computed_at":"2026-07-05T09:42:06.679533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:06.679533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nI734kzysGKqKPNp16ut0LJlOqK4aDURfqbZLZPvnS+3VXEXLIOILlrIxY85ZgWuUZxV0aLtVMF8Bhl8dKbsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:06.680046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeeab7555a625b51af21c7549b1a5e18058fc503ff70893c6494b54683590e51","sha256:318519b76a543dc2ca471d8fb1a9af26c929e29ffb556bb059eff8b4d6adfeeb"],"state_sha256":"3c6d6ec75b10490762b5ec5cd5077628da257669e58f0cf8258e3cb30b576986"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmBJL7OLAmdIN61jMl/1QD/vrJpGW4vmZKGuxVCdr0gUb69ZyDMiSpVUVB0WH3X8qbJ+QuT/kPYe06OasZK6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:08:32.486610Z","bundle_sha256":"1c2ede3042aa624508c66669d72c3a2610d9e589ecb0087583e6563f50f62369"}}