{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LPXAIE6WADMZTSIDV6WCUI4RVA","short_pith_number":"pith:LPXAIE6W","schema_version":"1.0","canonical_sha256":"5bee0413d600d999c903afac2a2391a830599026f10cf4b0d83352f08f847742","source":{"kind":"arxiv","id":"1710.04334","version":4},"attestation_state":"computed","paper":{"title":"DisSent: Sentence Representation Learning from Explicit Discourse Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allen Nie, Erin D. Bennett, Noah D. Goodman","submitted_at":"2017-10-12T00:56:13Z","abstract_excerpt":"Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show that with dependency parsing and rule-based rubrics, we can curate a high quality sentence relation task by leveraging explicit discourse relations. We show that our curated dataset provides an excellent signal for learning vector representations of sentence meaning, representing relations that can only be determined when the meanings of two sentences are comb"},"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":"1710.04334","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-12T00:56:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8268c887c340ac62d86a01e9a8f55584ce7888ac57cfa6927a591b2f13ef9490","abstract_canon_sha256":"77c27497a96ad49e9f0dbe8abc182ba36cdeb1612ce0e27127317f2782a56f02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:22.924912Z","signature_b64":"aowNpphT9BMhqkxbhkxk9YDO13Z2rsOgmUZS3ScqnUgCJAP48ZcLPd007ejIb/hcaVHOEe8dZd7vnbM9ZxXmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bee0413d600d999c903afac2a2391a830599026f10cf4b0d83352f08f847742","last_reissued_at":"2026-05-17T23:44:22.924147Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:22.924147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisSent: Sentence Representation Learning from Explicit Discourse Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Allen Nie, Erin D. Bennett, Noah D. Goodman","submitted_at":"2017-10-12T00:56:13Z","abstract_excerpt":"Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show that with dependency parsing and rule-based rubrics, we can curate a high quality sentence relation task by leveraging explicit discourse relations. We show that our curated dataset provides an excellent signal for learning vector representations of sentence meaning, representing relations that can only be determined when the meanings of two sentences are comb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04334","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.04334","created_at":"2026-05-17T23:44:22.924261+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.04334v4","created_at":"2026-05-17T23:44:22.924261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04334","created_at":"2026-05-17T23:44:22.924261+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPXAIE6WADMZ","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPXAIE6WADMZTSID","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPXAIE6W","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08340","citing_title":"Learning Compressed Sentence Representations for On-Device Text Processing","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"1804.07461","citing_title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA","json":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA.json","graph_json":"https://pith.science/api/pith-number/LPXAIE6WADMZTSIDV6WCUI4RVA/graph.json","events_json":"https://pith.science/api/pith-number/LPXAIE6WADMZTSIDV6WCUI4RVA/events.json","paper":"https://pith.science/paper/LPXAIE6W"},"agent_actions":{"view_html":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA","download_json":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA.json","view_paper":"https://pith.science/paper/LPXAIE6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.04334&json=true","fetch_graph":"https://pith.science/api/pith-number/LPXAIE6WADMZTSIDV6WCUI4RVA/graph.json","fetch_events":"https://pith.science/api/pith-number/LPXAIE6WADMZTSIDV6WCUI4RVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA/action/storage_attestation","attest_author":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA/action/author_attestation","sign_citation":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA/action/citation_signature","submit_replication":"https://pith.science/pith/LPXAIE6WADMZTSIDV6WCUI4RVA/action/replication_record"}},"created_at":"2026-05-17T23:44:22.924261+00:00","updated_at":"2026-05-17T23:44:22.924261+00:00"}