{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AQOC52XCXZLORCM6J6JNXSK43R","short_pith_number":"pith:AQOC52XC","schema_version":"1.0","canonical_sha256":"041c2eeae2be56e8899e4f92dbc95cdc665310f315674c8eb8a26dadd65ecc2e","source":{"kind":"arxiv","id":"2401.06782","version":1},"attestation_state":"computed","paper":{"title":"Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Liu, Chang Che, Liqiang Yu, Qunwei Lin, Xinyu Zhao","submitted_at":"2024-01-06T02:35:49Z","abstract_excerpt":"In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscores the persisting difficulties of CPC research.\n  To overcome these challenges and bolster the CPC system, This paper presents two key innovations. Firstly, it introduces an ensemble approach that inco"},"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":"2401.06782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T02:35:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"552d8fbd943224c22d6848a360e61a37dd86aaaa014e7cb980a2ec8478dcc17b","abstract_canon_sha256":"bf92d622326b7239fe5fae759dbc6fab924d0f3b14c2e079f9c1e536c1a4c821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:26.255291Z","signature_b64":"j6MoQ3NGGkTqwDamaM9DJ9i0cc+pSNAc8Ik9IOTtCXOqcMuQ8/0xouR2uK3l0+wWM02PCB1o3PuTHSRnB/67Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041c2eeae2be56e8899e4f92dbc95cdc665310f315674c8eb8a26dadd65ecc2e","last_reissued_at":"2026-07-05T07:33:26.254850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:26.254850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Liu, Chang Che, Liqiang Yu, Qunwei Lin, Xinyu Zhao","submitted_at":"2024-01-06T02:35:49Z","abstract_excerpt":"In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscores the persisting difficulties of CPC research.\n  To overcome these challenges and bolster the CPC system, This paper presents two key innovations. Firstly, it introduces an ensemble approach that inco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06782","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/2401.06782/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":"2401.06782","created_at":"2026-07-05T07:33:26.254909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06782v1","created_at":"2026-07-05T07:33:26.254909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06782","created_at":"2026-07-05T07:33:26.254909+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQOC52XCXZLO","created_at":"2026-07-05T07:33:26.254909+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQOC52XCXZLORCM6","created_at":"2026-07-05T07:33:26.254909+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQOC52XC","created_at":"2026-07-05T07:33:26.254909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18952","citing_title":"Legal Document Summarization: Enhancing Judicial Efficiency through Automation Detection","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R","json":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R.json","graph_json":"https://pith.science/api/pith-number/AQOC52XCXZLORCM6J6JNXSK43R/graph.json","events_json":"https://pith.science/api/pith-number/AQOC52XCXZLORCM6J6JNXSK43R/events.json","paper":"https://pith.science/paper/AQOC52XC"},"agent_actions":{"view_html":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R","download_json":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R.json","view_paper":"https://pith.science/paper/AQOC52XC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06782&json=true","fetch_graph":"https://pith.science/api/pith-number/AQOC52XCXZLORCM6J6JNXSK43R/graph.json","fetch_events":"https://pith.science/api/pith-number/AQOC52XCXZLORCM6J6JNXSK43R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R/action/storage_attestation","attest_author":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R/action/author_attestation","sign_citation":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R/action/citation_signature","submit_replication":"https://pith.science/pith/AQOC52XCXZLORCM6J6JNXSK43R/action/replication_record"}},"created_at":"2026-07-05T07:33:26.254909+00:00","updated_at":"2026-07-05T07:33:26.254909+00:00"}