{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZSQWWCTUZGLCVUQUX5ZHBFOHT","short_pith_number":"pith:UZSQWWCT","schema_version":"1.0","canonical_sha256":"a6650b5853a64cb15690a5fb9384ae3cec7a399a4e0d962ece29622ff7b007f6","source":{"kind":"arxiv","id":"2505.21646","version":2},"attestation_state":"computed","paper":{"title":"Iterative Corpus Refinement for Materials Property Prediction Based on Scientific Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.CL","authors_text":"Lei Zhang, Markus Stricker","submitted_at":"2025-05-27T18:20:58Z","abstract_excerpt":"The discovery and optimization of materials for specific applications is hampered by the practically infinite number of possible elemental combinations and associated properties, also known as the `combinatorial explosion'. By nature of the problem, data are scarce and all possible data sources should be used. In addition to simulations and experimental results, the latent knowledge in scientific texts is not yet used to its full potential. We present an iterative framework that refines a given scientific corpus by strategic selection of the most diverse documents, training Word2Vec models, an"},"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":"2505.21646","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T18:20:58Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"b8a189439306301213d9dd1c91695bf41078e0f513bcb10fb4d78028c0f89b65","abstract_canon_sha256":"f5d735908fcf0670b1f7c2bc383dcf4465a6bf0824a56c92a2d876b95b723212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:07.537652Z","signature_b64":"LuosqSG0D1KblaDE10Sr7Nl7Q9BHklwXxgAIxXh6dX8Tt+YW7CthqKbS+FM7Fy3Ps+3A6dBWp1l5ZfHHn/HbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6650b5853a64cb15690a5fb9384ae3cec7a399a4e0d962ece29622ff7b007f6","last_reissued_at":"2026-07-05T11:19:07.537030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:07.537030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Corpus Refinement for Materials Property Prediction Based on Scientific Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.CL","authors_text":"Lei Zhang, Markus Stricker","submitted_at":"2025-05-27T18:20:58Z","abstract_excerpt":"The discovery and optimization of materials for specific applications is hampered by the practically infinite number of possible elemental combinations and associated properties, also known as the `combinatorial explosion'. By nature of the problem, data are scarce and all possible data sources should be used. In addition to simulations and experimental results, the latent knowledge in scientific texts is not yet used to its full potential. We present an iterative framework that refines a given scientific corpus by strategic selection of the most diverse documents, training Word2Vec models, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21646","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/2505.21646/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.21646","created_at":"2026-07-05T11:19:07.537106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21646v2","created_at":"2026-07-05T11:19:07.537106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21646","created_at":"2026-07-05T11:19:07.537106+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZSQWWCTUZGL","created_at":"2026-07-05T11:19:07.537106+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZSQWWCTUZGLCVUQ","created_at":"2026-07-05T11:19:07.537106+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZSQWWCT","created_at":"2026-07-05T11:19:07.537106+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/UZSQWWCTUZGLCVUQUX5ZHBFOHT","json":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT.json","graph_json":"https://pith.science/api/pith-number/UZSQWWCTUZGLCVUQUX5ZHBFOHT/graph.json","events_json":"https://pith.science/api/pith-number/UZSQWWCTUZGLCVUQUX5ZHBFOHT/events.json","paper":"https://pith.science/paper/UZSQWWCT"},"agent_actions":{"view_html":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT","download_json":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT.json","view_paper":"https://pith.science/paper/UZSQWWCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21646&json=true","fetch_graph":"https://pith.science/api/pith-number/UZSQWWCTUZGLCVUQUX5ZHBFOHT/graph.json","fetch_events":"https://pith.science/api/pith-number/UZSQWWCTUZGLCVUQUX5ZHBFOHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT/action/storage_attestation","attest_author":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT/action/author_attestation","sign_citation":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT/action/citation_signature","submit_replication":"https://pith.science/pith/UZSQWWCTUZGLCVUQUX5ZHBFOHT/action/replication_record"}},"created_at":"2026-07-05T11:19:07.537106+00:00","updated_at":"2026-07-05T11:19:07.537106+00:00"}