{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EFIRRSZ4QIC7UE7FU6C374ZFMJ","short_pith_number":"pith:EFIRRSZ4","schema_version":"1.0","canonical_sha256":"215118cb3c8205fa13e5a785bff3256251eb7e7272fd3dc8e0d75162f50d5179","source":{"kind":"arxiv","id":"2509.09303","version":1},"attestation_state":"computed","paper":{"title":"From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grazia Sveva Ascione, Nicol\\`o Tamagnone","submitted_at":"2025-09-11T09:44:16Z","abstract_excerpt":"Classifying patents by their relevance to the UN Sustainable Development Goals (SDGs) is crucial for tracking how innovation addresses global challenges. However, the absence of a large, labeled dataset limits the use of supervised learning. Existing methods, such as keyword searches, transfer learning, and citation-based heuristics, lack scalability and generalizability. This paper frames patent-to-SDG classification as a weak supervision problem, using citations from patents to SDG-tagged scientific publications (NPL citations) as a noisy initial signal. To address its sparsity and noise, we"},"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":"2509.09303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T09:44:16Z","cross_cats_sorted":[],"title_canon_sha256":"d5b83ee40844d8b26441d43d282d9c51433f7d9fea091d3cf99505c1df7910f3","abstract_canon_sha256":"059fe7e3826c4a77e1c83601a31e6379f9b19868339def616aa6a4c088ee9ee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:33.580929Z","signature_b64":"cXgOAZ0Q9eN5oXP3HD7a5BgpxV6vtGAEmWz7CNybSBZmRqNSwajL1h7ZH5Ea+Sbu0oDE4c+hQWL28Zkz0GJ8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"215118cb3c8205fa13e5a785bff3256251eb7e7272fd3dc8e0d75162f50d5179","last_reissued_at":"2026-07-05T12:09:33.580442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:33.580442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grazia Sveva Ascione, Nicol\\`o Tamagnone","submitted_at":"2025-09-11T09:44:16Z","abstract_excerpt":"Classifying patents by their relevance to the UN Sustainable Development Goals (SDGs) is crucial for tracking how innovation addresses global challenges. However, the absence of a large, labeled dataset limits the use of supervised learning. Existing methods, such as keyword searches, transfer learning, and citation-based heuristics, lack scalability and generalizability. This paper frames patent-to-SDG classification as a weak supervision problem, using citations from patents to SDG-tagged scientific publications (NPL citations) as a noisy initial signal. To address its sparsity and noise, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09303","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/2509.09303/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":"2509.09303","created_at":"2026-07-05T12:09:33.580505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09303v1","created_at":"2026-07-05T12:09:33.580505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09303","created_at":"2026-07-05T12:09:33.580505+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFIRRSZ4QIC7","created_at":"2026-07-05T12:09:33.580505+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFIRRSZ4QIC7UE7F","created_at":"2026-07-05T12:09:33.580505+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFIRRSZ4","created_at":"2026-07-05T12:09:33.580505+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/EFIRRSZ4QIC7UE7FU6C374ZFMJ","json":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ.json","graph_json":"https://pith.science/api/pith-number/EFIRRSZ4QIC7UE7FU6C374ZFMJ/graph.json","events_json":"https://pith.science/api/pith-number/EFIRRSZ4QIC7UE7FU6C374ZFMJ/events.json","paper":"https://pith.science/paper/EFIRRSZ4"},"agent_actions":{"view_html":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ","download_json":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ.json","view_paper":"https://pith.science/paper/EFIRRSZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09303&json=true","fetch_graph":"https://pith.science/api/pith-number/EFIRRSZ4QIC7UE7FU6C374ZFMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EFIRRSZ4QIC7UE7FU6C374ZFMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ/action/storage_attestation","attest_author":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ/action/author_attestation","sign_citation":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ/action/citation_signature","submit_replication":"https://pith.science/pith/EFIRRSZ4QIC7UE7FU6C374ZFMJ/action/replication_record"}},"created_at":"2026-07-05T12:09:33.580505+00:00","updated_at":"2026-07-05T12:09:33.580505+00:00"}