{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ORNHLZFT6W4EQEUZCVTKH3WM2R","short_pith_number":"pith:ORNHLZFT","schema_version":"1.0","canonical_sha256":"745a75e4b3f5b84812991566a3eeccd440c0042e7ebb8c2e99b60746b0e41d47","source":{"kind":"arxiv","id":"2311.04335","version":1},"attestation_state":"computed","paper":{"title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Ben Zhou, Dan Roth, Dian Yu, Dong Yu, Hongming Zhang, Hongwei Wang, Sihao Chen, Tong Chen, Wenhao Yu","submitted_at":"2023-11-07T20:38:30Z","abstract_excerpt":"We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence of text is encoded into a fixed-length vector, the sub-sentence encoder learns to produce distinct contextual embeddings corresponding to different atomic propositions, i.e. atomic units of meaning expressed within a text sequence. The sub-sentence embeddings are contrastively learned to recognize (inferred) semantic equivalence between propositions across di"},"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":"2311.04335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T20:38:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"609ab274a2db88ed8e0d81c6dbfff07ba8004b855e56fd40ebb12b050d4f74fa","abstract_canon_sha256":"1c25a7a8c64901faebfd09b5fa37edc712378d6970d3dcc312dd6854bfdf9b7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:34.189448Z","signature_b64":"bpKwEnf+FZtTbz3RLC/emZWYdm7nn7rh/YXtFLw05MN45JIfxOl5L0L3i0IM5I3r25ybktUuudXChp2Z7alPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"745a75e4b3f5b84812991566a3eeccd440c0042e7ebb8c2e99b60746b0e41d47","last_reissued_at":"2026-07-05T07:10:34.188974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:34.188974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Ben Zhou, Dan Roth, Dian Yu, Dong Yu, Hongming Zhang, Hongwei Wang, Sihao Chen, Tong Chen, Wenhao Yu","submitted_at":"2023-11-07T20:38:30Z","abstract_excerpt":"We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence of text is encoded into a fixed-length vector, the sub-sentence encoder learns to produce distinct contextual embeddings corresponding to different atomic propositions, i.e. atomic units of meaning expressed within a text sequence. The sub-sentence embeddings are contrastively learned to recognize (inferred) semantic equivalence between propositions across di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04335","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/2311.04335/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":"2311.04335","created_at":"2026-07-05T07:10:34.189029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04335v1","created_at":"2026-07-05T07:10:34.189029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04335","created_at":"2026-07-05T07:10:34.189029+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORNHLZFT6W4E","created_at":"2026-07-05T07:10:34.189029+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORNHLZFT6W4EQEUZ","created_at":"2026-07-05T07:10:34.189029+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORNHLZFT","created_at":"2026-07-05T07:10:34.189029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19906","citing_title":"Evaluate Summarization in Fine-Granularity: Auto Evaluation with LLM","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R","json":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R.json","graph_json":"https://pith.science/api/pith-number/ORNHLZFT6W4EQEUZCVTKH3WM2R/graph.json","events_json":"https://pith.science/api/pith-number/ORNHLZFT6W4EQEUZCVTKH3WM2R/events.json","paper":"https://pith.science/paper/ORNHLZFT"},"agent_actions":{"view_html":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R","download_json":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R.json","view_paper":"https://pith.science/paper/ORNHLZFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04335&json=true","fetch_graph":"https://pith.science/api/pith-number/ORNHLZFT6W4EQEUZCVTKH3WM2R/graph.json","fetch_events":"https://pith.science/api/pith-number/ORNHLZFT6W4EQEUZCVTKH3WM2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R/action/storage_attestation","attest_author":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R/action/author_attestation","sign_citation":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R/action/citation_signature","submit_replication":"https://pith.science/pith/ORNHLZFT6W4EQEUZCVTKH3WM2R/action/replication_record"}},"created_at":"2026-07-05T07:10:34.189029+00:00","updated_at":"2026-07-05T07:10:34.189029+00:00"}