{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NZTD54ARSVIL3HPHFNP4F53RTB","short_pith_number":"pith:NZTD54AR","schema_version":"1.0","canonical_sha256":"6e663ef0119550bd9de72b5fc2f771986a0720098b72f2951cef2e5528f9b49a","source":{"kind":"arxiv","id":"2605.24297","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Amirhossein Yousefiramandi, Ciaran Cooney","submitted_at":"2026-05-22T23:51:13Z","abstract_excerpt":"Which fine-tuning signals improve patent embedding models, and do gains transfer across patent landscapes? We benchmark 22 embedding models, from 22M-parameter encoders to 12B instruction-tuned LLMs, on retrieval, classification, and clustering. The study uses 113,148 WIPO assistive-technology patents, 46,069 citation-graph retrieval queries, and the public DAPFAM dataset for external validation. Our framework covers citation-based retrieval, hybrid sparse-dense fusion, multi-label classification over five datasets, unsupervised clustering, six text-section views, domain-adaptive fine-tuning o"},"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":"2605.24297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-22T23:51:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dcca28111e3b4c09a5e69162797f26781c6d32d5af388754e09641778915c40b","abstract_canon_sha256":"c045f5746f29539c299ff15e4917bc2bb3035ec186db1df0afc433fdd3ab7dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:58.425603Z","signature_b64":"cX0zeu3ISkDoJiPaELDpCNaHoblbE1TuFYxbbS+a4OE+K4kbBtg2Mxn1htAMEGw9t782B8UVtnb57pZFOYKgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e663ef0119550bd9de72b5fc2f771986a0720098b72f2951cef2e5528f9b49a","last_reissued_at":"2026-05-26T01:02:58.424640Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:58.424640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Amirhossein Yousefiramandi, Ciaran Cooney","submitted_at":"2026-05-22T23:51:13Z","abstract_excerpt":"Which fine-tuning signals improve patent embedding models, and do gains transfer across patent landscapes? We benchmark 22 embedding models, from 22M-parameter encoders to 12B instruction-tuned LLMs, on retrieval, classification, and clustering. The study uses 113,148 WIPO assistive-technology patents, 46,069 citation-graph retrieval queries, and the public DAPFAM dataset for external validation. Our framework covers citation-based retrieval, hybrid sparse-dense fusion, multi-label classification over five datasets, unsupervised clustering, six text-section views, domain-adaptive fine-tuning o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24297","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/2605.24297/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":"2605.24297","created_at":"2026-05-26T01:02:58.424783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24297v1","created_at":"2026-05-26T01:02:58.424783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24297","created_at":"2026-05-26T01:02:58.424783+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZTD54ARSVIL","created_at":"2026-05-26T01:02:58.424783+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZTD54ARSVIL3HPH","created_at":"2026-05-26T01:02:58.424783+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZTD54AR","created_at":"2026-05-26T01:02:58.424783+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/NZTD54ARSVIL3HPHFNP4F53RTB","json":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB.json","graph_json":"https://pith.science/api/pith-number/NZTD54ARSVIL3HPHFNP4F53RTB/graph.json","events_json":"https://pith.science/api/pith-number/NZTD54ARSVIL3HPHFNP4F53RTB/events.json","paper":"https://pith.science/paper/NZTD54AR"},"agent_actions":{"view_html":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB","download_json":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB.json","view_paper":"https://pith.science/paper/NZTD54AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24297&json=true","fetch_graph":"https://pith.science/api/pith-number/NZTD54ARSVIL3HPHFNP4F53RTB/graph.json","fetch_events":"https://pith.science/api/pith-number/NZTD54ARSVIL3HPHFNP4F53RTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB/action/storage_attestation","attest_author":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB/action/author_attestation","sign_citation":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB/action/citation_signature","submit_replication":"https://pith.science/pith/NZTD54ARSVIL3HPHFNP4F53RTB/action/replication_record"}},"created_at":"2026-05-26T01:02:58.424783+00:00","updated_at":"2026-05-26T01:02:58.424783+00:00"}