{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JV2LRBMVW3GMTFHT7UGHK52X5U","short_pith_number":"pith:JV2LRBMV","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"},"canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","source":{"kind":"arxiv","id":"2501.15876","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JV2LRBMVW3GMTFHT7UGHK52X5U","target":"record","payload":{"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"},"canonical_sha256":"4d74b88595b6ccc994f3fd0c757757ed11134e0365219ec8f5dc1c94b138fed8","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"},"source_kind":"arxiv","source_id":"2501.15876","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WY++ya3/rYFjHgolht6KVLvO5RyYwbfJNPC+KkhoaEO79ofsObRWvx/Qwj8MwNgnC+Occte/AgdAoNYRJQYgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:16:58.683479Z"},"content_sha256":"616847d9660bb7d0b11b5d046f6c021ae50a16e7bf21e784d805cae1eb12327a","schema_version":"1.0","event_id":"sha256:616847d9660bb7d0b11b5d046f6c021ae50a16e7bf21e784d805cae1eb12327a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JV2LRBMVW3GMTFHT7UGHK52X5U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vaUb+8s6HoOFpKoRpbHSTILMZad/Le5g0w149YoRoeH4Clo4zEaM/r++TTz4APMUahDqREqENdN0Ae5TMg5wDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:16:58.684015Z"},"content_sha256":"8fd3011ffcc87c37a04628163b033a472c7eef59765316ffda21a1d42da472a5","schema_version":"1.0","event_id":"sha256:8fd3011ffcc87c37a04628163b033a472c7eef59765316ffda21a1d42da472a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/bundle.json","state_url":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T08:16:58Z","links":{"resolver":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U","bundle":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/bundle.json","state":"https://pith.science/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JV2LRBMVW3GMTFHT7UGHK52X5U/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVJuu0PSVEEaq35Qj8XsmPFLgOSZWvWISuemWkf857wZWQJlrkhqhQoAkhkx7DkYuLm+GUm2ZEmR/e+3Hv9kCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:16:58.687496Z","bundle_sha256":"49e7bd124ee43e1cd48890c30d483772454506ffc138ec243d89469a34d2d507"}}