{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MWPMWJYLA2HIR2IGLZMNCKYDUM","short_pith_number":"pith:MWPMWJYL","schema_version":"1.0","canonical_sha256":"659ecb270b068e88e9065e58d12b03a32c73e3bfe361aa27e85029dbf9378f56","source":{"kind":"arxiv","id":"1905.06939","version":2},"attestation_state":"computed","paper":{"title":"The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew McCallum, Edward Kim, Elsa Olivetti, Emma Strubell, Haw-Shiuan Chang, Jeffrey Flanigan, Kevin Huang, Sheshera Mysore, Zach Jensen","submitted_at":"2019-05-16T17:57:35Z","abstract_excerpt":"Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific understanding of materials synthesis and enable automated synthesis planning. Such analysis requires extracting structured representations of synthesis procedures from the raw text as a first step. To facilitate the training and evaluation of synthesis extraction models, we introduce a dataset of 230 synthesis procedures annotated by domain experts with labeled graphs that express "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.06939","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T17:57:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d81564c78fb32731aee1e1e4bd7e5dd4e2ca7b84f8727d723e5b5d47da670cec","abstract_canon_sha256":"710e116ce1e529e2426070f40142034f7bfd8b3c9d98f34ec576bdcb2a82c453"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:38.769259Z","signature_b64":"2etMP9iVHMuy1KR9n69p66Dggds062KedyjvEB+O1OJOA6ToYnecEpSIZxDltS1d0fNnYOQkuDnPZVbIz17jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"659ecb270b068e88e9065e58d12b03a32c73e3bfe361aa27e85029dbf9378f56","last_reissued_at":"2026-05-17T23:40:38.768561Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:38.768561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew McCallum, Edward Kim, Elsa Olivetti, Emma Strubell, Haw-Shiuan Chang, Jeffrey Flanigan, Kevin Huang, Sheshera Mysore, Zach Jensen","submitted_at":"2019-05-16T17:57:35Z","abstract_excerpt":"Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific understanding of materials synthesis and enable automated synthesis planning. Such analysis requires extracting structured representations of synthesis procedures from the raw text as a first step. To facilitate the training and evaluation of synthesis extraction models, we introduce a dataset of 230 synthesis procedures annotated by domain experts with labeled graphs that express "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06939","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.06939","created_at":"2026-05-17T23:40:38.768671+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06939v2","created_at":"2026-05-17T23:40:38.768671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06939","created_at":"2026-05-17T23:40:38.768671+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWPMWJYLA2HI","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWPMWJYLA2HIR2IG","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWPMWJYL","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM","json":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM.json","graph_json":"https://pith.science/api/pith-number/MWPMWJYLA2HIR2IGLZMNCKYDUM/graph.json","events_json":"https://pith.science/api/pith-number/MWPMWJYLA2HIR2IGLZMNCKYDUM/events.json","paper":"https://pith.science/paper/MWPMWJYL"},"agent_actions":{"view_html":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM","download_json":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM.json","view_paper":"https://pith.science/paper/MWPMWJYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06939&json=true","fetch_graph":"https://pith.science/api/pith-number/MWPMWJYLA2HIR2IGLZMNCKYDUM/graph.json","fetch_events":"https://pith.science/api/pith-number/MWPMWJYLA2HIR2IGLZMNCKYDUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM/action/storage_attestation","attest_author":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM/action/author_attestation","sign_citation":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM/action/citation_signature","submit_replication":"https://pith.science/pith/MWPMWJYLA2HIR2IGLZMNCKYDUM/action/replication_record"}},"created_at":"2026-05-17T23:40:38.768671+00:00","updated_at":"2026-05-17T23:40:38.768671+00:00"}