{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4WP225DGN2XRGHFSX3OZCESPUQ","short_pith_number":"pith:4WP225DG","schema_version":"1.0","canonical_sha256":"e59fad74666eaf131cb2bedd91124fa4188bc3fd766d5709ae3870c332bafc63","source":{"kind":"arxiv","id":"2202.02990","version":2},"attestation_state":"computed","paper":{"title":"Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano","submitted_at":"2022-02-07T08:15:48Z","abstract_excerpt":"There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on sem"},"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":"2202.02990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-07T08:15:48Z","cross_cats_sorted":[],"title_canon_sha256":"a257935f8fbf0cc9cc31590225836fa9fcde7161d85140876562b5c62c307057","abstract_canon_sha256":"4484e55d4980512e92076341df6e8cffd4e2b04e5db6e228779582361e31a3e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:40.694640Z","signature_b64":"Ec0XxuFzUL2fbbfvoQroSez9DB32uKFACiAIvI8lRkIZtyyW7shj9BHB0MlHLMN8NyrVGBFzmkcQsZkepLBADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e59fad74666eaf131cb2bedd91124fa4188bc3fd766d5709ae3870c332bafc63","last_reissued_at":"2026-07-05T04:30:40.694121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:40.694121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano","submitted_at":"2022-02-07T08:15:48Z","abstract_excerpt":"There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02990","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/2202.02990/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":"2202.02990","created_at":"2026-07-05T04:30:40.694199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02990v2","created_at":"2026-07-05T04:30:40.694199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02990","created_at":"2026-07-05T04:30:40.694199+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WP225DGN2XR","created_at":"2026-07-05T04:30:40.694199+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WP225DGN2XRGHFS","created_at":"2026-07-05T04:30:40.694199+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WP225DG","created_at":"2026-07-05T04:30:40.694199+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/4WP225DGN2XRGHFSX3OZCESPUQ","json":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ.json","graph_json":"https://pith.science/api/pith-number/4WP225DGN2XRGHFSX3OZCESPUQ/graph.json","events_json":"https://pith.science/api/pith-number/4WP225DGN2XRGHFSX3OZCESPUQ/events.json","paper":"https://pith.science/paper/4WP225DG"},"agent_actions":{"view_html":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ","download_json":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ.json","view_paper":"https://pith.science/paper/4WP225DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02990&json=true","fetch_graph":"https://pith.science/api/pith-number/4WP225DGN2XRGHFSX3OZCESPUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4WP225DGN2XRGHFSX3OZCESPUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ/action/storage_attestation","attest_author":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ/action/author_attestation","sign_citation":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ/action/citation_signature","submit_replication":"https://pith.science/pith/4WP225DGN2XRGHFSX3OZCESPUQ/action/replication_record"}},"created_at":"2026-07-05T04:30:40.694199+00:00","updated_at":"2026-07-05T04:30:40.694199+00:00"}