{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EILWVUCYQZ2S7Z5ZHW4RZO7Y6T","short_pith_number":"pith:EILWVUCY","canonical_record":{"source":{"id":"2607.00008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-04T20:55:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1610521b710cd7f23d9e8570d7e44eb81be2b529f67f016527ace386c0c65b4f","abstract_canon_sha256":"f492deb8ebe81e7486594be39cab45cfb55e5b8728fd759d225ae5fd65af2f9f"},"schema_version":"1.0"},"canonical_sha256":"22176ad05886752fe7b93db91cbbf8f4d423886eef38f3f3117976efc9acbd5b","source":{"kind":"arxiv","id":"2607.00008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00008","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00008v1","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00008","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"EILWVUCYQZ2S","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"EILWVUCYQZ2S7Z5Z","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"EILWVUCY","created_at":"2026-07-02T00:18:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EILWVUCYQZ2S7Z5ZHW4RZO7Y6T","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-04T20:55:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1610521b710cd7f23d9e8570d7e44eb81be2b529f67f016527ace386c0c65b4f","abstract_canon_sha256":"f492deb8ebe81e7486594be39cab45cfb55e5b8728fd759d225ae5fd65af2f9f"},"schema_version":"1.0"},"canonical_sha256":"22176ad05886752fe7b93db91cbbf8f4d423886eef38f3f3117976efc9acbd5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:04.362203Z","signature_b64":"IXfdMB4R8JfLF9kvo7VGUcVMxd1mmiDOF5Fs4vutn1ZOUt+WPnfntkjUISSK+zrhlebHlc07ygEtgEAwftl+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22176ad05886752fe7b93db91cbbf8f4d423886eef38f3f3117976efc9acbd5b","last_reissued_at":"2026-07-02T00:18:04.359293Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:04.359293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00008","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":"2026-07-02T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vm+R9HH2RKe8z9q/qVwapxmUnv+sISrCL2RwI7CU6SW+FJizoSjpyl7VgIzGQmGxgNshOc3r/bNDNTBYG7JiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:38:58.841388Z"},"content_sha256":"470477e90549f2bb3dbd1eb0a972dc2eb84ffbbdf267dfbae9fc20a28c6602b7","schema_version":"1.0","event_id":"sha256:470477e90549f2bb3dbd1eb0a972dc2eb84ffbbdf267dfbae9fc20a28c6602b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EILWVUCYQZ2S7Z5ZHW4RZO7Y6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Arlie Coles, Eric Marshall, Erik Larsson, Nathan Bodenstab, Paul Vozila, Sin Yu Bonnie Ho","submitted_at":"2026-05-04T20:55:50Z","abstract_excerpt":"Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples when available. We evaluate SchemaRAG on real-world health"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00008","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/2607.00008/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":"2026-07-02T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hctZ/5kP0ZcQy4EfH6NTeI2Rvbp/VRQZH/iJ5vp9bnbJ1O7eTIkz5jW7Wyu4a88PtNEPXXtuDTOpXMZzAU9oDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:38:58.841781Z"},"content_sha256":"d80c945c759c9346704759291cbddc74be24b049d35ea91a8e957a5b60ee7afe","schema_version":"1.0","event_id":"sha256:d80c945c759c9346704759291cbddc74be24b049d35ea91a8e957a5b60ee7afe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/bundle.json","state_url":"https://pith.science/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/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":"2026-08-20T17:38:58Z","links":{"resolver":"https://pith.science/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T","bundle":"https://pith.science/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/bundle.json","state":"https://pith.science/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EILWVUCYQZ2S7Z5ZHW4RZO7Y6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EILWVUCYQZ2S7Z5ZHW4RZO7Y6T","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":"f492deb8ebe81e7486594be39cab45cfb55e5b8728fd759d225ae5fd65af2f9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-04T20:55:50Z","title_canon_sha256":"1610521b710cd7f23d9e8570d7e44eb81be2b529f67f016527ace386c0c65b4f"},"schema_version":"1.0","source":{"id":"2607.00008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00008","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00008v1","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00008","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"EILWVUCYQZ2S","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"EILWVUCYQZ2S7Z5Z","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"EILWVUCY","created_at":"2026-07-02T00:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:d80c945c759c9346704759291cbddc74be24b049d35ea91a8e957a5b60ee7afe","target":"graph","created_at":"2026-07-02T00:18:04Z","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/2607.00008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples when available. We evaluate SchemaRAG on real-world health","authors_text":"Arlie Coles, Eric Marshall, Erik Larsson, Nathan Bodenstab, Paul Vozila, Sin Yu Bonnie Ho","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-04T20:55:50Z","title":"SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00008","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":"sha256:470477e90549f2bb3dbd1eb0a972dc2eb84ffbbdf267dfbae9fc20a28c6602b7","target":"record","created_at":"2026-07-02T00:18:04Z","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":"f492deb8ebe81e7486594be39cab45cfb55e5b8728fd759d225ae5fd65af2f9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-04T20:55:50Z","title_canon_sha256":"1610521b710cd7f23d9e8570d7e44eb81be2b529f67f016527ace386c0c65b4f"},"schema_version":"1.0","source":{"id":"2607.00008","kind":"arxiv","version":1}},"canonical_sha256":"22176ad05886752fe7b93db91cbbf8f4d423886eef38f3f3117976efc9acbd5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22176ad05886752fe7b93db91cbbf8f4d423886eef38f3f3117976efc9acbd5b","first_computed_at":"2026-07-02T00:18:04.359293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:04.359293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IXfdMB4R8JfLF9kvo7VGUcVMxd1mmiDOF5Fs4vutn1ZOUt+WPnfntkjUISSK+zrhlebHlc07ygEtgEAwftl+Cg==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:04.362203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:470477e90549f2bb3dbd1eb0a972dc2eb84ffbbdf267dfbae9fc20a28c6602b7","sha256:d80c945c759c9346704759291cbddc74be24b049d35ea91a8e957a5b60ee7afe"],"state_sha256":"13d0de7d958cd7948cb75db4e6390f724f1d3d7a6a5a02ab3fcb5c08dc6b416f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xX2WZHFMYj3b+bSS2mXIs/XYkHGGpvmNHt8pGVJoDAGS+aqE4HWdkAv0aHgQhkvj60VzBbZWA8+9R+8PtBoICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:38:58.845037Z","bundle_sha256":"cf60039bf863908d7401a6c290c61b62d3c474c87ca2e7636412a7839e00c08e"}}