{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CA4C7UWKC5YGR7E4LMRXFFPHLP","short_pith_number":"pith:CA4C7UWK","canonical_record":{"source":{"id":"2401.07128","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T18:09:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"862855069e1e3458e4e3d7ff42cf339e928ff81981a85c6ef61bfe9eb055d4db","abstract_canon_sha256":"1e34b56d0ffcb29c61318e23aaa3fdf1f706515cf3597603a29a73acc980a728"},"schema_version":"1.0"},"canonical_sha256":"10382fd2ca177068fc9c5b237295e75bdaa18c32f5b6a127d1be6207257c3dff","source":{"kind":"arxiv","id":"2401.07128","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07128","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07128v3","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07128","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"CA4C7UWKC5YG","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"CA4C7UWKC5YGR7E4","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"CA4C7UWK","created_at":"2026-07-05T09:15:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CA4C7UWKC5YGR7E4LMRXFFPHLP","target":"record","payload":{"canonical_record":{"source":{"id":"2401.07128","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T18:09:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"862855069e1e3458e4e3d7ff42cf339e928ff81981a85c6ef61bfe9eb055d4db","abstract_canon_sha256":"1e34b56d0ffcb29c61318e23aaa3fdf1f706515cf3597603a29a73acc980a728"},"schema_version":"1.0"},"canonical_sha256":"10382fd2ca177068fc9c5b237295e75bdaa18c32f5b6a127d1be6207257c3dff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:29.169484Z","signature_b64":"nk6yxEem+CqjA6lAIVoNjTZOPmlXvOTpEqs9DdLGnotu1g12jxa94qGFgPKhJ0yqYiVVwV2vmsnBQrkScpoFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10382fd2ca177068fc9c5b237295e75bdaa18c32f5b6a127d1be6207257c3dff","last_reissued_at":"2026-07-05T09:15:29.168939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:29.168939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.07128","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":"2026-07-05T09:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kiZz5fxy9AeJSbbfolv1+fS1bVj4gHMLXW4iS5Y1qaDOjy/3Kb0SlKklbTma1+l4JaAfuNV5P5vnw1vj13L0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:32.306335Z"},"content_sha256":"57269b407ff2244a85465da1016dfdf5c9810d5e31b6663ace37c7cd31701ed0","schema_version":"1.0","event_id":"sha256:57269b407ff2244a85465da1016dfdf5c9810d5e31b6663ace37c7cd31701ed0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CA4C7UWKC5YGR7E4LMRXFFPHLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Hang Wu, Jieyu Zhang, Joyce Ho, May D. Wang, Ran Xu, Wenqi Shi, Yuanda Zhu, Yuchen Zhuang, Yue Yu","submitted_at":"2024-01-13T18:09:05Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving. We propose EHRAgent, an LLM agent empowered with a code interface, to autonomously generate and execute code for multi-tabular reasoning within electronic health records (EHRs). First, we formulate an EHR question-answering task into a tool-use planning process, efficiently decomposing a complicated task into a sequence of manageable actions. By integrating interactive coding and execution feedback, EHRAgent lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07128","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/2401.07128/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":"2026-07-05T09:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G/8EPMlVEEmprcuUgiTmYfJmzUIKGY/IiPsUYdoPRYJa/L5BmUaFyVbn/2oj7pWvAHyPceTpHMclBQY/ulJlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:32.306848Z"},"content_sha256":"8698df078ac744a7d7d01de976c83643f39d4fa3734ca94766bd2a8e1ba3de7d","schema_version":"1.0","event_id":"sha256:8698df078ac744a7d7d01de976c83643f39d4fa3734ca94766bd2a8e1ba3de7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/bundle.json","state_url":"https://pith.science/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/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":"2026-08-08T18:41:32Z","links":{"resolver":"https://pith.science/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP","bundle":"https://pith.science/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/bundle.json","state":"https://pith.science/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CA4C7UWKC5YGR7E4LMRXFFPHLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CA4C7UWKC5YGR7E4LMRXFFPHLP","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":"1e34b56d0ffcb29c61318e23aaa3fdf1f706515cf3597603a29a73acc980a728","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T18:09:05Z","title_canon_sha256":"862855069e1e3458e4e3d7ff42cf339e928ff81981a85c6ef61bfe9eb055d4db"},"schema_version":"1.0","source":{"id":"2401.07128","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07128","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07128v3","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07128","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"CA4C7UWKC5YG","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"CA4C7UWKC5YGR7E4","created_at":"2026-07-05T09:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"CA4C7UWK","created_at":"2026-07-05T09:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:8698df078ac744a7d7d01de976c83643f39d4fa3734ca94766bd2a8e1ba3de7d","target":"graph","created_at":"2026-07-05T09:15:29Z","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/2401.07128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solving. We propose EHRAgent, an LLM agent empowered with a code interface, to autonomously generate and execute code for multi-tabular reasoning within electronic health records (EHRs). First, we formulate an EHR question-answering task into a tool-use planning process, efficiently decomposing a complicated task into a sequence of manageable actions. By integrating interactive coding and execution feedback, EHRAgent lear","authors_text":"Carl Yang, Hang Wu, Jieyu Zhang, Joyce Ho, May D. Wang, Ran Xu, Wenqi Shi, Yuanda Zhu, Yuchen Zhuang, Yue Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T18:09:05Z","title":"EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07128","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":"sha256:57269b407ff2244a85465da1016dfdf5c9810d5e31b6663ace37c7cd31701ed0","target":"record","created_at":"2026-07-05T09:15:29Z","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":"1e34b56d0ffcb29c61318e23aaa3fdf1f706515cf3597603a29a73acc980a728","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T18:09:05Z","title_canon_sha256":"862855069e1e3458e4e3d7ff42cf339e928ff81981a85c6ef61bfe9eb055d4db"},"schema_version":"1.0","source":{"id":"2401.07128","kind":"arxiv","version":3}},"canonical_sha256":"10382fd2ca177068fc9c5b237295e75bdaa18c32f5b6a127d1be6207257c3dff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10382fd2ca177068fc9c5b237295e75bdaa18c32f5b6a127d1be6207257c3dff","first_computed_at":"2026-07-05T09:15:29.168939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:29.168939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nk6yxEem+CqjA6lAIVoNjTZOPmlXvOTpEqs9DdLGnotu1g12jxa94qGFgPKhJ0yqYiVVwV2vmsnBQrkScpoFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:29.169484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07128","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57269b407ff2244a85465da1016dfdf5c9810d5e31b6663ace37c7cd31701ed0","sha256:8698df078ac744a7d7d01de976c83643f39d4fa3734ca94766bd2a8e1ba3de7d"],"state_sha256":"7385110913180b40eab5fd281ec235fd50ff630616aff40171a6d2314062edc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbnCe+72kMRpKdfqSagQVqxnrg+cU5f7DDkz2Q6ohDr4gFa01fNqZmyLD9YibiLaIerMQp0FpqHH6jfBNNf1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:41:32.311412Z","bundle_sha256":"34e135066b30a04e046fb0f528e47df9beded3ecc67b786c4c71bc778ff29d20"}}