{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QTNPH7APVPZKGNPXNAL55KP3FO","short_pith_number":"pith:QTNPH7AP","schema_version":"1.0","canonical_sha256":"84daf3fc0fabf2a335f76817dea9fb2b9f73dd9df13278a97ce9f176e3b0ad55","source":{"kind":"arxiv","id":"2605.24296","version":1},"attestation_state":"computed","paper":{"title":"When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Amirhossein Yousefiramandi, Ciaran Cooney","submitted_at":"2026-05-22T23:49:52Z","abstract_excerpt":"We study when LLM-generated synthetic data helps low-resource multi-label patent classification, separating true synthetic value from the confound that larger augmented sets can win by volume alone. Across six open-source LLMs (3.8-12B), four real-data regimes, 64 WIPO assistive-technology labels, two generation strategies, and three classifier families, the headline BERT-for-Patents micro-F1 jump from 0.120 to 0.702 is largely volume-driven. A duplicate-to-match real-only control that resamples 165 patents to the augmented size reaches 0.678; the controlled synthetic gain is only +0.024 over "},"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":"2605.24296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T23:49:52Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"0e7bdc50b15b2d5a4abcd9c087f8c21af8103079c62015fc87ad8e662a2e3c9f","abstract_canon_sha256":"dfbd4c175789ee08b9d259a51066cbb83fa7d09780c84ed58fec7ade1cdac4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:58.391528Z","signature_b64":"Z5+/A0H5VHs4flKMo5/83mCTkQG4ooLxW7kCtHhWe2yW+YMsaCin8yrrSy/S9fyMxRNe+l3xTk3zPeUqbaXFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84daf3fc0fabf2a335f76817dea9fb2b9f73dd9df13278a97ce9f176e3b0ad55","last_reissued_at":"2026-05-26T01:02:58.390851Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:58.390851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Amirhossein Yousefiramandi, Ciaran Cooney","submitted_at":"2026-05-22T23:49:52Z","abstract_excerpt":"We study when LLM-generated synthetic data helps low-resource multi-label patent classification, separating true synthetic value from the confound that larger augmented sets can win by volume alone. Across six open-source LLMs (3.8-12B), four real-data regimes, 64 WIPO assistive-technology labels, two generation strategies, and three classifier families, the headline BERT-for-Patents micro-F1 jump from 0.120 to 0.702 is largely volume-driven. A duplicate-to-match real-only control that resamples 165 patents to the augmented size reaches 0.678; the controlled synthetic gain is only +0.024 over "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24296","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/2605.24296/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":"2605.24296","created_at":"2026-05-26T01:02:58.390961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24296v1","created_at":"2026-05-26T01:02:58.390961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24296","created_at":"2026-05-26T01:02:58.390961+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTNPH7APVPZK","created_at":"2026-05-26T01:02:58.390961+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTNPH7APVPZKGNPX","created_at":"2026-05-26T01:02:58.390961+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTNPH7AP","created_at":"2026-05-26T01:02:58.390961+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/QTNPH7APVPZKGNPXNAL55KP3FO","json":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO.json","graph_json":"https://pith.science/api/pith-number/QTNPH7APVPZKGNPXNAL55KP3FO/graph.json","events_json":"https://pith.science/api/pith-number/QTNPH7APVPZKGNPXNAL55KP3FO/events.json","paper":"https://pith.science/paper/QTNPH7AP"},"agent_actions":{"view_html":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO","download_json":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO.json","view_paper":"https://pith.science/paper/QTNPH7AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24296&json=true","fetch_graph":"https://pith.science/api/pith-number/QTNPH7APVPZKGNPXNAL55KP3FO/graph.json","fetch_events":"https://pith.science/api/pith-number/QTNPH7APVPZKGNPXNAL55KP3FO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO/action/storage_attestation","attest_author":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO/action/author_attestation","sign_citation":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO/action/citation_signature","submit_replication":"https://pith.science/pith/QTNPH7APVPZKGNPXNAL55KP3FO/action/replication_record"}},"created_at":"2026-05-26T01:02:58.390961+00:00","updated_at":"2026-05-26T01:02:58.390961+00:00"}