{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GR3LEGRLXRKGJAV2Q7CMJMSQQO","short_pith_number":"pith:GR3LEGRL","schema_version":"1.0","canonical_sha256":"3476b21a2bbc546482ba87c4c4b25083a5a08119c95ce7f2d97c08a9c447ab98","source":{"kind":"arxiv","id":"2003.05019","version":1},"attestation_state":"computed","paper":{"title":"Text classification with word embedding regularization and soft similarity measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Eniafe Festus Ayetiran, Michal \\v{S}tef\\'anik, Petr Sojka, V\\'it Novotn\\'y","submitted_at":"2020-03-10T22:07:34Z","abstract_excerpt":"Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine measure (SCM) and the Word Mover's Distance (WMD), were reported to achieve state-of-the-art performance on semantic text similarity and text classification.\n  Despite the strong performance of the WMD on text classification and semantic text similarity, its super-cubic average time complexity is impractical. The SCM has quadratic worst-case time complexity, but i"},"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":"2003.05019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-03-10T22:07:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"669e420d4b0154f3bd4e1fbf64ad6992d80b17ebcd001a14928db98b68dd0a6b","abstract_canon_sha256":"194a5243bc0f93c7e04a92cc93b787005d401ce0c9d9c44c38d22a19bba4211e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:07.554807Z","signature_b64":"NWxU8NIEKM3Jg7YVODBzOqi0wlLl/lbPgansDH69rAl5rVnhxiAHY6MROI4f379pAjNUZKGJvFjVhe0x2BPqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3476b21a2bbc546482ba87c4c4b25083a5a08119c95ce7f2d97c08a9c447ab98","last_reissued_at":"2026-07-05T00:52:07.554410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:07.554410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text classification with word embedding regularization and soft similarity measure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Eniafe Festus Ayetiran, Michal \\v{S}tef\\'anik, Petr Sojka, V\\'it Novotn\\'y","submitted_at":"2020-03-10T22:07:34Z","abstract_excerpt":"Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine measure (SCM) and the Word Mover's Distance (WMD), were reported to achieve state-of-the-art performance on semantic text similarity and text classification.\n  Despite the strong performance of the WMD on text classification and semantic text similarity, its super-cubic average time complexity is impractical. The SCM has quadratic worst-case time complexity, but i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05019","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/2003.05019/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":"2003.05019","created_at":"2026-07-05T00:52:07.554472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.05019v1","created_at":"2026-07-05T00:52:07.554472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05019","created_at":"2026-07-05T00:52:07.554472+00:00"},{"alias_kind":"pith_short_12","alias_value":"GR3LEGRLXRKG","created_at":"2026-07-05T00:52:07.554472+00:00"},{"alias_kind":"pith_short_16","alias_value":"GR3LEGRLXRKGJAV2","created_at":"2026-07-05T00:52:07.554472+00:00"},{"alias_kind":"pith_short_8","alias_value":"GR3LEGRL","created_at":"2026-07-05T00:52:07.554472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18931","citing_title":"Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO","json":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO.json","graph_json":"https://pith.science/api/pith-number/GR3LEGRLXRKGJAV2Q7CMJMSQQO/graph.json","events_json":"https://pith.science/api/pith-number/GR3LEGRLXRKGJAV2Q7CMJMSQQO/events.json","paper":"https://pith.science/paper/GR3LEGRL"},"agent_actions":{"view_html":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO","download_json":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO.json","view_paper":"https://pith.science/paper/GR3LEGRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.05019&json=true","fetch_graph":"https://pith.science/api/pith-number/GR3LEGRLXRKGJAV2Q7CMJMSQQO/graph.json","fetch_events":"https://pith.science/api/pith-number/GR3LEGRLXRKGJAV2Q7CMJMSQQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO/action/storage_attestation","attest_author":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO/action/author_attestation","sign_citation":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO/action/citation_signature","submit_replication":"https://pith.science/pith/GR3LEGRLXRKGJAV2Q7CMJMSQQO/action/replication_record"}},"created_at":"2026-07-05T00:52:07.554472+00:00","updated_at":"2026-07-05T00:52:07.554472+00:00"}