{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PREKHBMG7XDWS46AJX5N3RTF4O","short_pith_number":"pith:PREKHBMG","canonical_record":{"source":{"id":"2407.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-23T22:23:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e08c6ca09399bdf9a70fc9cb6b59a9980e6bc3f47411d099a82203f0f935a02","abstract_canon_sha256":"44dad70ba749ef2a64a0edfa3afc745128174d7d03f8c5c7478992950c4f7734"},"schema_version":"1.0"},"canonical_sha256":"7c48a38586fdc76973c04dfaddc665e3a0c7dcac911ede36043deb857589918c","source":{"kind":"arxiv","id":"2407.16867","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16867","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16867v2","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16867","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"PREKHBMG7XDW","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"PREKHBMG7XDWS46A","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"PREKHBMG","created_at":"2026-07-05T09:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PREKHBMG7XDWS46AJX5N3RTF4O","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-23T22:23:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e08c6ca09399bdf9a70fc9cb6b59a9980e6bc3f47411d099a82203f0f935a02","abstract_canon_sha256":"44dad70ba749ef2a64a0edfa3afc745128174d7d03f8c5c7478992950c4f7734"},"schema_version":"1.0"},"canonical_sha256":"7c48a38586fdc76973c04dfaddc665e3a0c7dcac911ede36043deb857589918c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:08.867847Z","signature_b64":"dxvjxFPXSAAIO4TrG8Pg+8H0RtVY/85OsjBIxnHvLniweH740NnbgcoNw6clEkyf2lLOMJorwBQ8mkRVvIkbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c48a38586fdc76973c04dfaddc665e3a0c7dcac911ede36043deb857589918c","last_reissued_at":"2026-07-05T09:43:08.867286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:08.867286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16867","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCHA/WiYQ/3Xsw+70IGc1P+1woIsACq6TfgO5vegW9t0C+HGv2/hhXbDReIuOzMUBNACmasDDGStSfDsQh0aCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:12:39.018484Z"},"content_sha256":"1165b23c643392dd876737d6acd1a974aca3897240dc5d27c2ac99b05f64200c","schema_version":"1.0","event_id":"sha256:1165b23c643392dd876737d6acd1a974aca3897240dc5d27c2ac99b05f64200c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PREKHBMG7XDWS46AJX5N3RTF4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Text to Insight: Large Language Models for Materials Science Data Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Christoph T. Koch, Jos\\'e A. M\\'arquez, Kevin Maik Jablonka, Mara Schilling-Wilhelmi, Mar\\'ia Victoria Gil, Marti\\~no R\\'ios-Garc\\'ia, Santiago Miret, Sherjeel Shabih","submitted_at":"2024-07-23T22:23:47Z","abstract_excerpt":"The vast majority of materials science knowledge exists in unstructured natural language, yet structured data is crucial for innovative and systematic materials design. Traditionally, the field has relied on manual curation and partial automation for data extraction for specific use cases. The advent of large language models (LLMs) represents a significant shift, potentially enabling efficient extraction of structured, actionable data from unstructured text by non-experts. While applying LLMs to materials science data extraction presents unique challenges, domain knowledge offers opportunities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16867","kind":"arxiv","version":2},"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/2407.16867/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":"2026-07-05T09:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Q4S5bNhyxQRUpNfrx5raz5m4EzCD+XNUL4cPObNf1kOo6aYH9qVRvUXteH6Gh91HLUcKyKDKGW66Ptlf8BgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:12:39.018868Z"},"content_sha256":"22e61bf073d08284f766a58033291a4fb834d9f9d409f8af6b4713a0deb156a4","schema_version":"1.0","event_id":"sha256:22e61bf073d08284f766a58033291a4fb834d9f9d409f8af6b4713a0deb156a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PREKHBMG7XDWS46AJX5N3RTF4O/bundle.json","state_url":"https://pith.science/pith/PREKHBMG7XDWS46AJX5N3RTF4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PREKHBMG7XDWS46AJX5N3RTF4O/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":"2026-08-07T05:12:39Z","links":{"resolver":"https://pith.science/pith/PREKHBMG7XDWS46AJX5N3RTF4O","bundle":"https://pith.science/pith/PREKHBMG7XDWS46AJX5N3RTF4O/bundle.json","state":"https://pith.science/pith/PREKHBMG7XDWS46AJX5N3RTF4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PREKHBMG7XDWS46AJX5N3RTF4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PREKHBMG7XDWS46AJX5N3RTF4O","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":"44dad70ba749ef2a64a0edfa3afc745128174d7d03f8c5c7478992950c4f7734","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-23T22:23:47Z","title_canon_sha256":"3e08c6ca09399bdf9a70fc9cb6b59a9980e6bc3f47411d099a82203f0f935a02"},"schema_version":"1.0","source":{"id":"2407.16867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16867","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16867v2","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16867","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"PREKHBMG7XDW","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"PREKHBMG7XDWS46A","created_at":"2026-07-05T09:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"PREKHBMG","created_at":"2026-07-05T09:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:22e61bf073d08284f766a58033291a4fb834d9f9d409f8af6b4713a0deb156a4","target":"graph","created_at":"2026-07-05T09:43:08Z","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/2407.16867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast majority of materials science knowledge exists in unstructured natural language, yet structured data is crucial for innovative and systematic materials design. Traditionally, the field has relied on manual curation and partial automation for data extraction for specific use cases. The advent of large language models (LLMs) represents a significant shift, potentially enabling efficient extraction of structured, actionable data from unstructured text by non-experts. While applying LLMs to materials science data extraction presents unique challenges, domain knowledge offers opportunities","authors_text":"Christoph T. Koch, Jos\\'e A. M\\'arquez, Kevin Maik Jablonka, Mara Schilling-Wilhelmi, Mar\\'ia Victoria Gil, Marti\\~no R\\'ios-Garc\\'ia, Santiago Miret, Sherjeel Shabih","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-23T22:23:47Z","title":"From Text to Insight: Large Language Models for Materials Science Data Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16867","kind":"arxiv","version":2},"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":"sha256:1165b23c643392dd876737d6acd1a974aca3897240dc5d27c2ac99b05f64200c","target":"record","created_at":"2026-07-05T09:43:08Z","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":"44dad70ba749ef2a64a0edfa3afc745128174d7d03f8c5c7478992950c4f7734","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-23T22:23:47Z","title_canon_sha256":"3e08c6ca09399bdf9a70fc9cb6b59a9980e6bc3f47411d099a82203f0f935a02"},"schema_version":"1.0","source":{"id":"2407.16867","kind":"arxiv","version":2}},"canonical_sha256":"7c48a38586fdc76973c04dfaddc665e3a0c7dcac911ede36043deb857589918c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c48a38586fdc76973c04dfaddc665e3a0c7dcac911ede36043deb857589918c","first_computed_at":"2026-07-05T09:43:08.867286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:08.867286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dxvjxFPXSAAIO4TrG8Pg+8H0RtVY/85OsjBIxnHvLniweH740NnbgcoNw6clEkyf2lLOMJorwBQ8mkRVvIkbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:08.867847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1165b23c643392dd876737d6acd1a974aca3897240dc5d27c2ac99b05f64200c","sha256:22e61bf073d08284f766a58033291a4fb834d9f9d409f8af6b4713a0deb156a4"],"state_sha256":"298126eae4a655577422388e4e252384df817fb507680efbd05f9774498faac5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/dX9LMwm5LhVTvCPsvyeHfDCTF3UUmA9L9pwuG2dLEfgi4Mc1Tp6MkS9a/fzxsiyCsktiLiKar3j658tFDNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:12:39.021676Z","bundle_sha256":"1c1721f6588325d7668f56ea89ed03b224fcd2451257644b0afc267e42730260"}}