{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RWTMVVWBDDH57QLCIPJEO4EVEG","short_pith_number":"pith:RWTMVVWB","schema_version":"1.0","canonical_sha256":"8da6cad6c118cfdfc16243d247709521b32e5ecbf64ce269985f2111faad779b","source":{"kind":"arxiv","id":"2402.19462","version":2},"attestation_state":"computed","paper":{"title":"Accelerating materials discovery for polymer solar cells: Data-driven insights enabled by natural language processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","physics.app-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aishat Adeboye, Chao Zhang, Pranav Shetty, Rampi Ramprasad, Sonakshi Gupta","submitted_at":"2024-02-29T18:54:46Z","abstract_excerpt":"We present a simulation of various active learning strategies for the discovery of polymer solar cell donor/acceptor pairs using data extracted from the literature spanning $\\sim$20 years by a natural language processing pipeline. While data-driven methods have been well established to discover novel materials faster than Edisonian trial-and-error approaches, their benefits have not been quantified for material discovery problems that can take decades. Our approach demonstrates a potential reduction in discovery time by approximately 75 %, equivalent to a 15 year acceleration in material innov"},"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":"2402.19462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-02-29T18:54:46Z","cross_cats_sorted":["cs.CL","physics.app-ph"],"title_canon_sha256":"f1a984ba0c4d62abf3d43469de31da7fae81ef84c5560de475285a9ff56e37c2","abstract_canon_sha256":"6b3033c2deaf3584490b34be9a43b7fce0df8e9ffd960ededa1685509beb56a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:52.366920Z","signature_b64":"BF5jRsGfx30fzOHVLLilm6y+GBDE0vNNxIG7b6RNRQdwzLXmBm5ZD8c9dbMYIdVZq6B0/vhXvR0Qvql60id5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8da6cad6c118cfdfc16243d247709521b32e5ecbf64ce269985f2111faad779b","last_reissued_at":"2026-07-05T08:52:52.366445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:52.366445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating materials discovery for polymer solar cells: Data-driven insights enabled by natural language processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","physics.app-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aishat Adeboye, Chao Zhang, Pranav Shetty, Rampi Ramprasad, Sonakshi Gupta","submitted_at":"2024-02-29T18:54:46Z","abstract_excerpt":"We present a simulation of various active learning strategies for the discovery of polymer solar cell donor/acceptor pairs using data extracted from the literature spanning $\\sim$20 years by a natural language processing pipeline. While data-driven methods have been well established to discover novel materials faster than Edisonian trial-and-error approaches, their benefits have not been quantified for material discovery problems that can take decades. Our approach demonstrates a potential reduction in discovery time by approximately 75 %, equivalent to a 15 year acceleration in material innov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19462","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/2402.19462/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":"2402.19462","created_at":"2026-07-05T08:52:52.366509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19462v2","created_at":"2026-07-05T08:52:52.366509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19462","created_at":"2026-07-05T08:52:52.366509+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWTMVVWBDDH5","created_at":"2026-07-05T08:52:52.366509+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWTMVVWBDDH57QLC","created_at":"2026-07-05T08:52:52.366509+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWTMVVWB","created_at":"2026-07-05T08:52:52.366509+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/RWTMVVWBDDH57QLCIPJEO4EVEG","json":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG.json","graph_json":"https://pith.science/api/pith-number/RWTMVVWBDDH57QLCIPJEO4EVEG/graph.json","events_json":"https://pith.science/api/pith-number/RWTMVVWBDDH57QLCIPJEO4EVEG/events.json","paper":"https://pith.science/paper/RWTMVVWB"},"agent_actions":{"view_html":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG","download_json":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG.json","view_paper":"https://pith.science/paper/RWTMVVWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19462&json=true","fetch_graph":"https://pith.science/api/pith-number/RWTMVVWBDDH57QLCIPJEO4EVEG/graph.json","fetch_events":"https://pith.science/api/pith-number/RWTMVVWBDDH57QLCIPJEO4EVEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG/action/storage_attestation","attest_author":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG/action/author_attestation","sign_citation":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG/action/citation_signature","submit_replication":"https://pith.science/pith/RWTMVVWBDDH57QLCIPJEO4EVEG/action/replication_record"}},"created_at":"2026-07-05T08:52:52.366509+00:00","updated_at":"2026-07-05T08:52:52.366509+00:00"}