{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JV2LRBMVW3GMTFHT7UGHK52X5U","short_pith_number":"pith:JV2LRBMV","schema_version":"1.0","canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","source":{"kind":"arxiv","id":"2501.15876","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lifu Gao, Qi Zhang, Ziwei Liu","submitted_at":"2025-01-27T09:02:42Z","abstract_excerpt":"Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble techniques to improve sentence embeddings. We use external data from SimpleWiki, Wikipedia, and BookCorpus to make sure the training data is consistent. The framework includes a hierarchical model with an encoding layer, refinement layer, and ensemble prediction layer, using ALBERT-xxlarge, RoBERTa-large, and DeBERTa-large models. Cross-attention layers 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":"2501.15876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T09:02:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a31a862fe93bd161d0b95d7f789a68547237aaa7b14167d84bdfbb40ad88f0f6","abstract_canon_sha256":"fe94ade9ae775868f0e97dbddda425498c50565f55ac31b20b81c698fb62616a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:51.502662Z","signature_b64":"SHKVH4hEagdmH0KsbKDuB8hIE+0iMF5Qi60aWKnqwowsVHsmTchZdTIOoxK+7wWqKIURzJzezNI/zQPi37OzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","last_reissued_at":"2026-07-05T10:05:51.502179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:51.502179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lifu Gao, Qi Zhang, Ziwei Liu","submitted_at":"2025-01-27T09:02:42Z","abstract_excerpt":"Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble techniques to improve sentence embeddings. We use external data from SimpleWiki, Wikipedia, and BookCorpus to make sure the training data is consistent. The framework includes a hierarchical model with an encoding layer, refinement layer, and ensemble prediction layer, using ALBERT-xxlarge, RoBERTa-large, and DeBERTa-large models. Cross-attention layers com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15876","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/2501.15876/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":"2501.15876","created_at":"2026-07-05T10:05:51.502236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15876v1","created_at":"2026-07-05T10:05:51.502236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15876","created_at":"2026-07-05T10:05:51.502236+00:00"},{"alias_kind":"pith_short_12","alias_value":"JV2LRBMVW3GM","created_at":"2026-07-05T10:05:51.502236+00:00"},{"alias_kind":"pith_short_16","alias_value":"JV2LRBMVW3GMTFHT","created_at":"2026-07-05T10:05:51.502236+00:00"},{"alias_kind":"pith_short_8","alias_value":"JV2LRBMV","created_at":"2026-07-05T10:05:51.502236+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/JV2LRBMVW3GMTFHT7UGHK52X5U","json":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U.json","graph_json":"https://pith.science/api/pith-number/JV2LRBMVW3GMTFHT7UGHK52X5U/graph.json","events_json":"https://pith.science/api/pith-number/JV2LRBMVW3GMTFHT7UGHK52X5U/events.json","paper":"https://pith.science/paper/JV2LRBMV"},"agent_actions":{"view_html":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U","download_json":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U.json","view_paper":"https://pith.science/paper/JV2LRBMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15876&json=true","fetch_graph":"https://pith.science/api/pith-number/JV2LRBMVW3GMTFHT7UGHK52X5U/graph.json","fetch_events":"https://pith.science/api/pith-number/JV2LRBMVW3GMTFHT7UGHK52X5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/action/storage_attestation","attest_author":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/action/author_attestation","sign_citation":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/action/citation_signature","submit_replication":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/action/replication_record"}},"created_at":"2026-07-05T10:05:51.502236+00:00","updated_at":"2026-07-05T10:05:51.502236+00:00"}