{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N7QYLHGP2PB6GVQPUB6SR67XPK","short_pith_number":"pith:N7QYLHGP","canonical_record":{"source":{"id":"2409.00847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d93abe01835b552fb7191533068599bdad47a0f709ec27c41872e7ff6e052a8d","abstract_canon_sha256":"437b0ef0de5bcdfc10f0526daa925c23b262388356f1df80e1ddf34ab863cdb2"},"schema_version":"1.0"},"canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","source":{"kind":"arxiv","id":"2409.00847","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00847","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00847v3","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00847","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"N7QYLHGP2PB6","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"N7QYLHGP2PB6GVQP","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"N7QYLHGP","created_at":"2026-07-05T09:54:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N7QYLHGP2PB6GVQPUB6SR67XPK","target":"record","payload":{"canonical_record":{"source":{"id":"2409.00847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d93abe01835b552fb7191533068599bdad47a0f709ec27c41872e7ff6e052a8d","abstract_canon_sha256":"437b0ef0de5bcdfc10f0526daa925c23b262388356f1df80e1ddf34ab863cdb2"},"schema_version":"1.0"},"canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:46.652984Z","signature_b64":"BQ/gEs4kLmABCOhoX4gAQCso89ZEbqI8BiTIwZHDrsq2E6HEuH9h+HoHaJ1WXK4eW++dOsvq62Nl7ak1w734CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","last_reissued_at":"2026-07-05T09:54:46.652485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:46.652485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.00847","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t2v5O9rpsdM1OI1n/RhRwKcEClaNGhrkoTfWbC/gWLfeyn3dK0pW+odq8jAqhO30NdiJLURuBnFCaE3fxTWMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:30.141674Z"},"content_sha256":"c996c8a403d526ec70154186115894218875d34555e11ff1990a1127a19e42c8","schema_version":"1.0","event_id":"sha256:c996c8a403d526ec70154186115894218875d34555e11ff1990a1127a19e42c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N7QYLHGP2PB6GVQPUB6SR67XPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Design of an LLM-powered Unstructured Analytics System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Alex Meyer, Austin Lee, Benjamin Sowell, Bohou Li, Dan Tecuci, Eric Anderson, Henry Lindeman, Jonathan Fritz, Mark Lindblad, Matt Welsh, Mehul A. Shah, Parth Parmar, Tanvi Ranade, Vinayak Thapliyal","submitted_at":"2024-09-01T21:30:14Z","abstract_excerpt":"LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents. At the core of Aryn is Sycamore, a declarative document processing engine, that provides a reliable distributed abstrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00847","kind":"arxiv","version":3},"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/2409.00847/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":"2026-07-05T09:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vmRnovrZqO3TCB9a2M4YO14mwA+Nx/WrRSW8mi5msV4+SXrSHZmvdsxn995stGm5LBdGVYBo6nbHrs/yFUvOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:56:30.142590Z"},"content_sha256":"40990295047465ef828089de015e8022ac660b4c55b76bf3c76913d17164707a","schema_version":"1.0","event_id":"sha256:40990295047465ef828089de015e8022ac660b4c55b76bf3c76913d17164707a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/bundle.json","state_url":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/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":"2026-08-09T04:56:30Z","links":{"resolver":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK","bundle":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/bundle.json","state":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N7QYLHGP2PB6GVQPUB6SR67XPK","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":"437b0ef0de5bcdfc10f0526daa925c23b262388356f1df80e1ddf34ab863cdb2","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","title_canon_sha256":"d93abe01835b552fb7191533068599bdad47a0f709ec27c41872e7ff6e052a8d"},"schema_version":"1.0","source":{"id":"2409.00847","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00847","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00847v3","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00847","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"N7QYLHGP2PB6","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"N7QYLHGP2PB6GVQP","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"N7QYLHGP","created_at":"2026-07-05T09:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:40990295047465ef828089de015e8022ac660b4c55b76bf3c76913d17164707a","target":"graph","created_at":"2026-07-05T09:54:46Z","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/2409.00847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents. At the core of Aryn is Sycamore, a declarative document processing engine, that provides a reliable distributed abstrac","authors_text":"Alex Meyer, Austin Lee, Benjamin Sowell, Bohou Li, Dan Tecuci, Eric Anderson, Henry Lindeman, Jonathan Fritz, Mark Lindblad, Matt Welsh, Mehul A. Shah, Parth Parmar, Tanvi Ranade, Vinayak Thapliyal","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","title":"The Design of an LLM-powered Unstructured Analytics System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00847","kind":"arxiv","version":3},"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:c996c8a403d526ec70154186115894218875d34555e11ff1990a1127a19e42c8","target":"record","created_at":"2026-07-05T09:54:46Z","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":"437b0ef0de5bcdfc10f0526daa925c23b262388356f1df80e1ddf34ab863cdb2","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","title_canon_sha256":"d93abe01835b552fb7191533068599bdad47a0f709ec27c41872e7ff6e052a8d"},"schema_version":"1.0","source":{"id":"2409.00847","kind":"arxiv","version":3}},"canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","first_computed_at":"2026-07-05T09:54:46.652485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:46.652485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BQ/gEs4kLmABCOhoX4gAQCso89ZEbqI8BiTIwZHDrsq2E6HEuH9h+HoHaJ1WXK4eW++dOsvq62Nl7ak1w734CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:46.652984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00847","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c996c8a403d526ec70154186115894218875d34555e11ff1990a1127a19e42c8","sha256:40990295047465ef828089de015e8022ac660b4c55b76bf3c76913d17164707a"],"state_sha256":"f2a238e90d8217f16a2297c17fbe8fe46cc0c4865cfe383787dbf4045eccc260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"br9LdP97EKaBSpdZ7SsaitE07FZ0WJMYF1GjE0+N4jOQLkxGjidzKXZ98Yq+fWbGOibGUYMpPgqsLKAUCAciDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:56:30.172427Z","bundle_sha256":"7030d7b26ed14fd259494ae88d78c6d91bcf0147c0127aca84fa7a626a284318"}}