{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CEWHQTK6LBOPX62UK6O2C4MO2Q","short_pith_number":"pith:CEWHQTK6","schema_version":"1.0","canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","source":{"kind":"arxiv","id":"1906.03656","version":1},"attestation_state":"computed","paper":{"title":"Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohit Iyyer, Tu Vu","submitted_at":"2019-06-09T15:18:53Z","abstract_excerpt":"While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method proposed by Zhang et al. (2017) and discover that it cannot reliably tell whether a given sentence occurs in the input paragraph or not. We formulate a sentence content task to probe for this basic linguistic property and find that even a much simpler bag-of-words method has no trouble solving it. This result motivates us to replace the reconstruction-based objec"},"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":"1906.03656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-09T15:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"3219151239fee2b5d573c05edadde527b784d240afab3267d3a3db08df282099","abstract_canon_sha256":"82a7126fc6257406a39dbd8a5b0153b2b1dd2ddc026f2d64fded601e6bfa288f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:45.474868Z","signature_b64":"0rynu7iFwj9EngRrKynOT21UNg+T8VHh6+HDhBAt00DT/uv/R2RtT/aI2yJcI7BYmotsMZvTvlxbFqNADMlQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","last_reissued_at":"2026-05-17T23:43:45.474212Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:45.474212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohit Iyyer, Tu Vu","submitted_at":"2019-06-09T15:18:53Z","abstract_excerpt":"While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method proposed by Zhang et al. (2017) and discover that it cannot reliably tell whether a given sentence occurs in the input paragraph or not. We formulate a sentence content task to probe for this basic linguistic property and find that even a much simpler bag-of-words method has no trouble solving it. This result motivates us to replace the reconstruction-based objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03656","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":""},"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":"1906.03656","created_at":"2026-05-17T23:43:45.474334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03656v1","created_at":"2026-05-17T23:43:45.474334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03656","created_at":"2026-05-17T23:43:45.474334+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEWHQTK6LBOP","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEWHQTK6LBOPX62U","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEWHQTK6","created_at":"2026-05-18T12:33:12.712433+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/CEWHQTK6LBOPX62UK6O2C4MO2Q","json":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q.json","graph_json":"https://pith.science/api/pith-number/CEWHQTK6LBOPX62UK6O2C4MO2Q/graph.json","events_json":"https://pith.science/api/pith-number/CEWHQTK6LBOPX62UK6O2C4MO2Q/events.json","paper":"https://pith.science/paper/CEWHQTK6"},"agent_actions":{"view_html":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q","download_json":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q.json","view_paper":"https://pith.science/paper/CEWHQTK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03656&json=true","fetch_graph":"https://pith.science/api/pith-number/CEWHQTK6LBOPX62UK6O2C4MO2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/CEWHQTK6LBOPX62UK6O2C4MO2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/action/storage_attestation","attest_author":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/action/author_attestation","sign_citation":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/action/citation_signature","submit_replication":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/action/replication_record"}},"created_at":"2026-05-17T23:43:45.474334+00:00","updated_at":"2026-05-17T23:43:45.474334+00:00"}