{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JLHLPPEPY35D6QCXQPBXF2D4B4","short_pith_number":"pith:JLHLPPEP","canonical_record":{"source":{"id":"2402.16671","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"486a96a4134c715d2ba25cf928b102d6a5fa3d016968a71efbc5d3afdeb8ec79","abstract_canon_sha256":"5a26be78a38f145465e29dc3c9582ed45f3b97fd668697d834b1b97900a95b1a"},"schema_version":"1.0"},"canonical_sha256":"4aceb7bc8fc6fa3f405783c372e87c0f128267a5acda9e788f9a8269a6530b9e","source":{"kind":"arxiv","id":"2402.16671","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16671","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16671v7","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16671","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"JLHLPPEPY35D","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"JLHLPPEPY35D6QCX","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"JLHLPPEP","created_at":"2026-07-05T09:16:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JLHLPPEPY35D6QCXQPBXF2D4B4","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16671","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"486a96a4134c715d2ba25cf928b102d6a5fa3d016968a71efbc5d3afdeb8ec79","abstract_canon_sha256":"5a26be78a38f145465e29dc3c9582ed45f3b97fd668697d834b1b97900a95b1a"},"schema_version":"1.0"},"canonical_sha256":"4aceb7bc8fc6fa3f405783c372e87c0f128267a5acda9e788f9a8269a6530b9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:46.645533Z","signature_b64":"bfgREfn8AHzNZ8aprn9NwV1lTmbePVX4VZAJ/Qkx+kCXFjHx+ZNr/tVnUSF0wz484lqEAWKwaNIQEUwqsjtwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aceb7bc8fc6fa3f405783c372e87c0f128267a5acda9e788f9a8269a6530b9e","last_reissued_at":"2026-07-05T09:16:46.645113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:46.645113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16671","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQhkUJ3alIUFAWXRvWc+6k/ZX1sWm0j9rvNRd/U9W37GcOVXqcHfyIWK9rB4DVNZgT/MgegQPKFd9pV8fA71Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:47:44.659802Z"},"content_sha256":"315e018bdde5b30ff9d5fd0786b20080999b55f96616fb482397b32c12b4d827","schema_version":"1.0","event_id":"sha256:315e018bdde5b30ff9d5fd0786b20080999b55f96616fb482397b32c12b4d827"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JLHLPPEPY35D6QCXQPBXF2D4B4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Zhuang, Ge Zhang, Jie Fu, Junjie Wang, Stephen W. Huang, Tianyu Zheng, Weiming Ren, Wenhu Chen, Xiang Yue, Xinrun Du","submitted_at":"2024-02-26T15:47:01Z","abstract_excerpt":"Structured data sources, such as tables, graphs, and databases, are ubiquitous knowledge sources. Despite the demonstrated capabilities of large language models (LLMs) on plain text, their proficiency in interpreting and utilizing structured data remains limited. Our investigation reveals a notable deficiency in LLMs' ability to process structured data, e.g., ChatGPT lags behind state-of-the-art (SoTA) model by an average of 35%. To augment the Structured Knowledge Grounding (SKG) capabilities in LLMs, we have developed a comprehensive instruction tuning dataset comprising 1.1 million examples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16671","kind":"arxiv","version":7},"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/2402.16671/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":"2026-07-05T09:16:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4w8wynMH72+mGO208B+1h4vp3RRsU583l0zu8HyKW0E8jJDGlPYH0IpKP4LVxvUFmWhJ5EGbtnnRD7DnnjAHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:47:44.660458Z"},"content_sha256":"ce1e4a8944279870334c4f0a65a08eb98d8a4d7a878560810a6e7a7805eccbae","schema_version":"1.0","event_id":"sha256:ce1e4a8944279870334c4f0a65a08eb98d8a4d7a878560810a6e7a7805eccbae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/bundle.json","state_url":"https://pith.science/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/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":"2026-08-06T00:47:44Z","links":{"resolver":"https://pith.science/pith/JLHLPPEPY35D6QCXQPBXF2D4B4","bundle":"https://pith.science/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/bundle.json","state":"https://pith.science/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLHLPPEPY35D6QCXQPBXF2D4B4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JLHLPPEPY35D6QCXQPBXF2D4B4","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":"5a26be78a38f145465e29dc3c9582ed45f3b97fd668697d834b1b97900a95b1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T15:47:01Z","title_canon_sha256":"486a96a4134c715d2ba25cf928b102d6a5fa3d016968a71efbc5d3afdeb8ec79"},"schema_version":"1.0","source":{"id":"2402.16671","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16671","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16671v7","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16671","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"JLHLPPEPY35D","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"JLHLPPEPY35D6QCX","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"JLHLPPEP","created_at":"2026-07-05T09:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce1e4a8944279870334c4f0a65a08eb98d8a4d7a878560810a6e7a7805eccbae","target":"graph","created_at":"2026-07-05T09:16:46Z","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/2402.16671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structured data sources, such as tables, graphs, and databases, are ubiquitous knowledge sources. Despite the demonstrated capabilities of large language models (LLMs) on plain text, their proficiency in interpreting and utilizing structured data remains limited. Our investigation reveals a notable deficiency in LLMs' ability to process structured data, e.g., ChatGPT lags behind state-of-the-art (SoTA) model by an average of 35%. To augment the Structured Knowledge Grounding (SKG) capabilities in LLMs, we have developed a comprehensive instruction tuning dataset comprising 1.1 million examples","authors_text":"Alex Zhuang, Ge Zhang, Jie Fu, Junjie Wang, Stephen W. Huang, Tianyu Zheng, Weiming Ren, Wenhu Chen, Xiang Yue, Xinrun Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T15:47:01Z","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16671","kind":"arxiv","version":7},"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":"sha256:315e018bdde5b30ff9d5fd0786b20080999b55f96616fb482397b32c12b4d827","target":"record","created_at":"2026-07-05T09:16:46Z","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":"5a26be78a38f145465e29dc3c9582ed45f3b97fd668697d834b1b97900a95b1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T15:47:01Z","title_canon_sha256":"486a96a4134c715d2ba25cf928b102d6a5fa3d016968a71efbc5d3afdeb8ec79"},"schema_version":"1.0","source":{"id":"2402.16671","kind":"arxiv","version":7}},"canonical_sha256":"4aceb7bc8fc6fa3f405783c372e87c0f128267a5acda9e788f9a8269a6530b9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aceb7bc8fc6fa3f405783c372e87c0f128267a5acda9e788f9a8269a6530b9e","first_computed_at":"2026-07-05T09:16:46.645113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:46.645113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bfgREfn8AHzNZ8aprn9NwV1lTmbePVX4VZAJ/Qkx+kCXFjHx+ZNr/tVnUSF0wz484lqEAWKwaNIQEUwqsjtwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:46.645533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16671","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:315e018bdde5b30ff9d5fd0786b20080999b55f96616fb482397b32c12b4d827","sha256:ce1e4a8944279870334c4f0a65a08eb98d8a4d7a878560810a6e7a7805eccbae"],"state_sha256":"e57841ec6fe9ad65d2fb4f9dd612114f6bb7b756848d04d498db9456c4cab4bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkTg9JFJrLc9gXcVzmuhLJppnhI/PmdU/NQGyC3wED09r9SVVp04KEF8Pg2eLT1ulpgJCtEv9yS0+ESL1dzqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:47:44.666218Z","bundle_sha256":"abc3530ca9d56f4a999f8629233f6ce00abb243c45561daaec1b47ea94362872"}}