{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EDS7EGYEI2ZMFVRBZQQUKIULFX","short_pith_number":"pith:EDS7EGYE","canonical_record":{"source":{"id":"2311.13778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-11-23T02:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"3aa78231e4d6ee574d8785f1335a8d6d27b179b849e837d3c4674f94d6f88d0c","abstract_canon_sha256":"6e06fa942369a6e4b055b1aeb6b7876d0be040877764493af1108aa779037db8"},"schema_version":"1.0"},"canonical_sha256":"20e5f21b0446b2c2d621cc2145228b2def2434d87b6861fc139ff77f01cac4d7","source":{"kind":"arxiv","id":"2311.13778","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13778","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13778v1","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13778","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"EDS7EGYEI2ZM","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"EDS7EGYEI2ZMFVRB","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"EDS7EGYE","created_at":"2026-07-05T07:16:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EDS7EGYEI2ZMFVRBZQQUKIULFX","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-11-23T02:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"3aa78231e4d6ee574d8785f1335a8d6d27b179b849e837d3c4674f94d6f88d0c","abstract_canon_sha256":"6e06fa942369a6e4b055b1aeb6b7876d0be040877764493af1108aa779037db8"},"schema_version":"1.0"},"canonical_sha256":"20e5f21b0446b2c2d621cc2145228b2def2434d87b6861fc139ff77f01cac4d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:07.900489Z","signature_b64":"kaClMxmKcSS7299iEo0WJ8cqghB2U+AygHJ+1aNdEaM63S1rZNQDh1cBQVtrbN0Eyp+5RDfHS6yipnSUQCb5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20e5f21b0446b2c2d621cc2145228b2def2434d87b6861fc139ff77f01cac4d7","last_reissued_at":"2026-07-05T07:16:07.900005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:07.900005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13778","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":"2026-07-05T07:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MAUepLNKoJKtISShfu5W3FU5EIG2xtEdDxexafaBf+5AXlFwE5QCuIfdhwG+2XdDwKk+DxwquD1Bs7vCtIaXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:43:24.718714Z"},"content_sha256":"858acf158a6257b9e290e605c49f817f607ab58431463fdb446dd6e3ae3d12e1","schema_version":"1.0","event_id":"sha256:858acf158a6257b9e290e605c49f817f607ab58431463fdb446dd6e3ae3d12e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EDS7EGYEI2ZMFVRBZQQUKIULFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accurate Prediction of Experimental Band Gaps from Large Language Model-Based Data Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Amil Merchant, Ekin Dogus Cubuk, Gowoon Cheon, Muratahan Aykol, Samuel J. Yang, Shutong Li, Subhashini Venugopalan, Vahe Tshitoyan","submitted_at":"2023-11-23T02:36:01Z","abstract_excerpt":"Machine learning is transforming materials discovery by providing rapid predictions of material properties, which enables large-scale screening for target materials. However, such models require training data. While automated data extraction from scientific literature has potential, current auto-generated datasets often lack sufficient accuracy and critical structural and processing details of materials that influence the properties. Using band gap as an example, we demonstrate Large language model (LLM)-prompt-based extraction yields an order of magnitude lower error rate. Combined with addit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13778","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/2311.13778/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":"2026-07-05T07:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glqAstj4AZvU3ckEyp7D2sQHAS6MNllrjbiteOeoPqVqUfCRXxIVHxjnx85LFSJWp2jBOFMceR/Qblm57t46Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:43:24.719087Z"},"content_sha256":"8bdb6cf08db732cad16642a78bc0b51725ea7022743d968346257971c763d86c","schema_version":"1.0","event_id":"sha256:8bdb6cf08db732cad16642a78bc0b51725ea7022743d968346257971c763d86c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/bundle.json","state_url":"https://pith.science/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/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":"2026-07-07T15:43:24Z","links":{"resolver":"https://pith.science/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX","bundle":"https://pith.science/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/bundle.json","state":"https://pith.science/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDS7EGYEI2ZMFVRBZQQUKIULFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EDS7EGYEI2ZMFVRBZQQUKIULFX","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":"6e06fa942369a6e4b055b1aeb6b7876d0be040877764493af1108aa779037db8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-11-23T02:36:01Z","title_canon_sha256":"3aa78231e4d6ee574d8785f1335a8d6d27b179b849e837d3c4674f94d6f88d0c"},"schema_version":"1.0","source":{"id":"2311.13778","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13778","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13778v1","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13778","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"EDS7EGYEI2ZM","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"EDS7EGYEI2ZMFVRB","created_at":"2026-07-05T07:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"EDS7EGYE","created_at":"2026-07-05T07:16:07Z"}],"graph_snapshots":[{"event_id":"sha256:8bdb6cf08db732cad16642a78bc0b51725ea7022743d968346257971c763d86c","target":"graph","created_at":"2026-07-05T07:16:07Z","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/2311.13778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning is transforming materials discovery by providing rapid predictions of material properties, which enables large-scale screening for target materials. However, such models require training data. While automated data extraction from scientific literature has potential, current auto-generated datasets often lack sufficient accuracy and critical structural and processing details of materials that influence the properties. Using band gap as an example, we demonstrate Large language model (LLM)-prompt-based extraction yields an order of magnitude lower error rate. Combined with addit","authors_text":"Amil Merchant, Ekin Dogus Cubuk, Gowoon Cheon, Muratahan Aykol, Samuel J. Yang, Shutong Li, Subhashini Venugopalan, Vahe Tshitoyan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-11-23T02:36:01Z","title":"Accurate Prediction of Experimental Band Gaps from Large Language Model-Based Data Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13778","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":"sha256:858acf158a6257b9e290e605c49f817f607ab58431463fdb446dd6e3ae3d12e1","target":"record","created_at":"2026-07-05T07:16:07Z","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":"6e06fa942369a6e4b055b1aeb6b7876d0be040877764493af1108aa779037db8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-11-23T02:36:01Z","title_canon_sha256":"3aa78231e4d6ee574d8785f1335a8d6d27b179b849e837d3c4674f94d6f88d0c"},"schema_version":"1.0","source":{"id":"2311.13778","kind":"arxiv","version":1}},"canonical_sha256":"20e5f21b0446b2c2d621cc2145228b2def2434d87b6861fc139ff77f01cac4d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20e5f21b0446b2c2d621cc2145228b2def2434d87b6861fc139ff77f01cac4d7","first_computed_at":"2026-07-05T07:16:07.900005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:07.900005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kaClMxmKcSS7299iEo0WJ8cqghB2U+AygHJ+1aNdEaM63S1rZNQDh1cBQVtrbN0Eyp+5RDfHS6yipnSUQCb5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:07.900489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13778","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:858acf158a6257b9e290e605c49f817f607ab58431463fdb446dd6e3ae3d12e1","sha256:8bdb6cf08db732cad16642a78bc0b51725ea7022743d968346257971c763d86c"],"state_sha256":"9ad5088a7b034367214c26abbfaa9611bd6cdc013a3008abf0c7424376e350e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bi5KwaF1Dg7n8i7ykXFyG/6QwHyO41duJSQaT00FLqKTiM9eUFutg/DOJov6hPS90XZMKxnPmOF7MBJ2AKr8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:43:24.721122Z","bundle_sha256":"1308b0866e38d5f307328255b30e44200540ad29d71ec8db3ce6bfa26ae5c784"}}