{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CDOYVE55Y6MWYU52GJ5OTVQM4I","short_pith_number":"pith:CDOYVE55","schema_version":"1.0","canonical_sha256":"10dd8a93bdc7996c53ba327ae9d60ce21e47c90af0a268535ea00a0f795a54ed","source":{"kind":"arxiv","id":"2303.05391","version":2},"attestation_state":"computed","paper":{"title":"Disambiguation of Company names via Deep Recurrent Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alessandro Basile, Alessandro Mercanti, Andrea Cosentini, Daniele Regoli, Michele Grasso, Riccardo Crupi, Shuyi Yang, Simone Scarsi","submitted_at":"2023-03-07T15:07:57Z","abstract_excerpt":"Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e. real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same com"},"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":"2303.05391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T15:07:57Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"55300b510614701a4f34117c9ab77fa2e8cc39588bd2f4855636efd33705491b","abstract_canon_sha256":"be73bdcf1086f98e0a9c9adb4ced2fe63a72e3e5b9652213df0787e6576f1f56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:52.584873Z","signature_b64":"DoOivfk1YDlAqABVCCI58TPQEQz6R+xMrpRheIsex7VyzdzMDNT32Y23WnWciu74+/FCqn/92MY745Mcc1P4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10dd8a93bdc7996c53ba327ae9d60ce21e47c90af0a268535ea00a0f795a54ed","last_reissued_at":"2026-07-05T07:14:52.584311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:52.584311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disambiguation of Company names via Deep Recurrent Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alessandro Basile, Alessandro Mercanti, Andrea Cosentini, Daniele Regoli, Michele Grasso, Riccardo Crupi, Shuyi Yang, Simone Scarsi","submitted_at":"2023-03-07T15:07:57Z","abstract_excerpt":"Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e. real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05391","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/2303.05391/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":"2303.05391","created_at":"2026-07-05T07:14:52.584386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05391v2","created_at":"2026-07-05T07:14:52.584386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05391","created_at":"2026-07-05T07:14:52.584386+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDOYVE55Y6MW","created_at":"2026-07-05T07:14:52.584386+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDOYVE55Y6MWYU52","created_at":"2026-07-05T07:14:52.584386+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDOYVE55","created_at":"2026-07-05T07:14:52.584386+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/CDOYVE55Y6MWYU52GJ5OTVQM4I","json":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I.json","graph_json":"https://pith.science/api/pith-number/CDOYVE55Y6MWYU52GJ5OTVQM4I/graph.json","events_json":"https://pith.science/api/pith-number/CDOYVE55Y6MWYU52GJ5OTVQM4I/events.json","paper":"https://pith.science/paper/CDOYVE55"},"agent_actions":{"view_html":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I","download_json":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I.json","view_paper":"https://pith.science/paper/CDOYVE55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05391&json=true","fetch_graph":"https://pith.science/api/pith-number/CDOYVE55Y6MWYU52GJ5OTVQM4I/graph.json","fetch_events":"https://pith.science/api/pith-number/CDOYVE55Y6MWYU52GJ5OTVQM4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I/action/storage_attestation","attest_author":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I/action/author_attestation","sign_citation":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I/action/citation_signature","submit_replication":"https://pith.science/pith/CDOYVE55Y6MWYU52GJ5OTVQM4I/action/replication_record"}},"created_at":"2026-07-05T07:14:52.584386+00:00","updated_at":"2026-07-05T07:14:52.584386+00:00"}