{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JV2LRBMVW3GMTFHT7UGHK52X5U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe94ade9ae775868f0e97dbddda425498c50565f55ac31b20b81c698fb62616a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T09:02:42Z","title_canon_sha256":"a31a862fe93bd161d0b95d7f789a68547237aaa7b14167d84bdfbb40ad88f0f6"},"schema_version":"1.0","source":{"id":"2501.15876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15876","created_at":"2026-07-05T10:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15876v1","created_at":"2026-07-05T10:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15876","created_at":"2026-07-05T10:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"JV2LRBMVW3GM","created_at":"2026-07-05T10:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"JV2LRBMVW3GMTFHT","created_at":"2026-07-05T10:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"JV2LRBMV","created_at":"2026-07-05T10:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:8fd3011ffcc87c37a04628163b033a472c7eef59765316ffda21a1d42da472a5","target":"graph","created_at":"2026-07-05T10:05:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.15876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lifu Gao, Qi Zhang, Ziwei Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T09:02:42Z","title":"Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15876","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:616847d9660bb7d0b11b5d046f6c021ae50a16e7bf21e784d805cae1eb12327a","target":"record","created_at":"2026-07-05T10:05:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe94ade9ae775868f0e97dbddda425498c50565f55ac31b20b81c698fb62616a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T09:02:42Z","title_canon_sha256":"a31a862fe93bd161d0b95d7f789a68547237aaa7b14167d84bdfbb40ad88f0f6"},"schema_version":"1.0","source":{"id":"2501.15876","kind":"arxiv","version":1}},"canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","first_computed_at":"2026-07-05T10:05:51.502179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:51.502179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SHKVH4hEagdmH0KsbKDuB8hIE+0iMF5Qi60aWKnqwowsVHsmTchZdTIOoxK+7wWqKIURzJzezNI/zQPi37OzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:51.502662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:616847d9660bb7d0b11b5d046f6c021ae50a16e7bf21e784d805cae1eb12327a","sha256:8fd3011ffcc87c37a04628163b033a472c7eef59765316ffda21a1d42da472a5"],"state_sha256":"9eafc203e96c9379693d52c1ff7a885ad29037cf43ae261c61e478cc216b6f3d"}