{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J7KYL46UF4NOK5TRJ6E4DOCKY2","short_pith_number":"pith:J7KYL46U","canonical_record":{"source":{"id":"2507.03674","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:51:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74947e7cf4a5d78048dfa2a269d49df886d78fa969a379d47d2725e85921ca73","abstract_canon_sha256":"b31291f8657626f566b3909a301c34c1e26bc04495183ad8750f1f5ad7bd2d02"},"schema_version":"1.0"},"canonical_sha256":"4fd585f3d42f1ae576714f89c1b84ac6af27978529ca7c2759a83d2a8edcc864","source":{"kind":"arxiv","id":"2507.03674","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03674","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03674v3","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03674","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"J7KYL46UF4NO","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_16","alias_value":"J7KYL46UF4NOK5TR","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_8","alias_value":"J7KYL46U","created_at":"2026-05-22T01:03:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J7KYL46UF4NOK5TRJ6E4DOCKY2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03674","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:51:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74947e7cf4a5d78048dfa2a269d49df886d78fa969a379d47d2725e85921ca73","abstract_canon_sha256":"b31291f8657626f566b3909a301c34c1e26bc04495183ad8750f1f5ad7bd2d02"},"schema_version":"1.0"},"canonical_sha256":"4fd585f3d42f1ae576714f89c1b84ac6af27978529ca7c2759a83d2a8edcc864","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:14.933537Z","signature_b64":"2slaCQIvj4QD1N9it3XPf9UzB3u7C+iUkwGNUHfeuT5TKfKHHxZpoWiVTatVr3EN+uSEkkjV7GWWLP1ubzauAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fd585f3d42f1ae576714f89c1b84ac6af27978529ca7c2759a83d2a8edcc864","last_reissued_at":"2026-05-22T01:03:14.932904Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:14.932904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03674","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":"2026-05-22T01:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2Ro5QQjV9gCARtYb/JIJUjzPGLoDyYcG2ZK8JNKrHh/ccatryoYD896zyQmOdwRYSMcgwAHrIxFyHX6DXE7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:11:41.690833Z"},"content_sha256":"c6c6003158f3a513ab6a8131f608d0a59612708ea01420fb7933b65c26b0d107","schema_version":"1.0","event_id":"sha256:c6c6003158f3a513ab6a8131f608d0a59612708ea01420fb7933b65c26b0d107"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J7KYL46UF4NOK5TRJ6E4DOCKY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dorota Jarecka, Lydia Ng, Patrick Ray, Puja Trivedi, Saif Haobsh, Satrajit S. Ghosh, Tek Raj Chhetri, Yibei Chen","submitted_at":"2025-07-04T15:51:07Z","abstract_excerpt":"Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle in specialized domains that require expert knowledge and generalize poorly across tasks. We introduce \\textsc{StructSense}, a modular, task-agnostic, open-source framework that integrates ontology-guided symbolic knowledge, agentic self-evaluative refinement, and human-in-the-loop validation for robust domain-aware extraction. We evaluate \\textsc{StructSense} on three tasks of increasing semantic complexity: schema-based extraction of assessment i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03674","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/2507.03674/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":"2026-05-22T01:03:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b1CWGTpLv53keY5VdP0DmyKPNBAgisC4zGhpSKohyTz9qzdP4dUc3gG5k7sz1GHrIQFRnyHyZXygtekhg5ZtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:11:41.691551Z"},"content_sha256":"b213866565b160ecd2b5ccc9dbbd64f99cb2d093349eac1098510ace99addeaf","schema_version":"1.0","event_id":"sha256:b213866565b160ecd2b5ccc9dbbd64f99cb2d093349eac1098510ace99addeaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/bundle.json","state_url":"https://pith.science/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/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":"2026-06-04T03:11:41Z","links":{"resolver":"https://pith.science/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2","bundle":"https://pith.science/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/bundle.json","state":"https://pith.science/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7KYL46UF4NOK5TRJ6E4DOCKY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7KYL46UF4NOK5TRJ6E4DOCKY2","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":"b31291f8657626f566b3909a301c34c1e26bc04495183ad8750f1f5ad7bd2d02","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:51:07Z","title_canon_sha256":"74947e7cf4a5d78048dfa2a269d49df886d78fa969a379d47d2725e85921ca73"},"schema_version":"1.0","source":{"id":"2507.03674","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03674","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03674v3","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03674","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"J7KYL46UF4NO","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_16","alias_value":"J7KYL46UF4NOK5TR","created_at":"2026-05-22T01:03:14Z"},{"alias_kind":"pith_short_8","alias_value":"J7KYL46U","created_at":"2026-05-22T01:03:14Z"}],"graph_snapshots":[{"event_id":"sha256:b213866565b160ecd2b5ccc9dbbd64f99cb2d093349eac1098510ace99addeaf","target":"graph","created_at":"2026-05-22T01:03:14Z","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/2507.03674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle in specialized domains that require expert knowledge and generalize poorly across tasks. We introduce \\textsc{StructSense}, a modular, task-agnostic, open-source framework that integrates ontology-guided symbolic knowledge, agentic self-evaluative refinement, and human-in-the-loop validation for robust domain-aware extraction. We evaluate \\textsc{StructSense} on three tasks of increasing semantic complexity: schema-based extraction of assessment i","authors_text":"Dorota Jarecka, Lydia Ng, Patrick Ray, Puja Trivedi, Saif Haobsh, Satrajit S. Ghosh, Tek Raj Chhetri, Yibei Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:51:07Z","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03674","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:c6c6003158f3a513ab6a8131f608d0a59612708ea01420fb7933b65c26b0d107","target":"record","created_at":"2026-05-22T01:03:14Z","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":"b31291f8657626f566b3909a301c34c1e26bc04495183ad8750f1f5ad7bd2d02","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:51:07Z","title_canon_sha256":"74947e7cf4a5d78048dfa2a269d49df886d78fa969a379d47d2725e85921ca73"},"schema_version":"1.0","source":{"id":"2507.03674","kind":"arxiv","version":3}},"canonical_sha256":"4fd585f3d42f1ae576714f89c1b84ac6af27978529ca7c2759a83d2a8edcc864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fd585f3d42f1ae576714f89c1b84ac6af27978529ca7c2759a83d2a8edcc864","first_computed_at":"2026-05-22T01:03:14.932904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:14.932904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2slaCQIvj4QD1N9it3XPf9UzB3u7C+iUkwGNUHfeuT5TKfKHHxZpoWiVTatVr3EN+uSEkkjV7GWWLP1ubzauAw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:14.933537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03674","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6c6003158f3a513ab6a8131f608d0a59612708ea01420fb7933b65c26b0d107","sha256:b213866565b160ecd2b5ccc9dbbd64f99cb2d093349eac1098510ace99addeaf"],"state_sha256":"e11da73dfc7fa250648e55f564f1347f87ffee62840e4b4e65810240796204ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VpB62cfkOPd3cn4IrX6qA4H5HzT6Xd4nrIlZ6u2vTUk30XiyS/j0S6P58HYa31NNGvB/ZkcbQPNIUQ4MYaAyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T03:11:41.694822Z","bundle_sha256":"b1096c13b9857ba6cf3013f34474d37dcdd4ab7830e0ebbe32fef1170b9bb526"}}