{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CEWHQTK6LBOPX62UK6O2C4MO2Q","short_pith_number":"pith:CEWHQTK6","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"},"canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","source":{"kind":"arxiv","id":"1906.03656","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03656","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03656v1","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03656","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"CEWHQTK6LBOP","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEWHQTK6LBOPX62U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEWHQTK6","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CEWHQTK6LBOPX62UK6O2C4MO2Q","target":"record","payload":{"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"},"canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","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"},"source_kind":"arxiv","source_id":"1906.03656","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":"2026-05-17T23:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PiQowgWKZi1V8HPtBEiZLqYtrcDlNItBTEr/kqOcmE/w0NombjQOWozyAMXbfoUcsKTIFggnYp59DFcQP2jEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:19:03.830853Z"},"content_sha256":"d582dc018cafc9403a666babe96b0ea0d7cdb9931371f753f0e81d72324e12f1","schema_version":"1.0","event_id":"sha256:d582dc018cafc9403a666babe96b0ea0d7cdb9931371f753f0e81d72324e12f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CEWHQTK6LBOPX62UK6O2C4MO2Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pGEbHYMxDcUQWr103pamqtZLBm9d+FFbL9L2qFpsneJe7fGrVKug/Ibz3rsqL1ZO5ZSWgwecwHQJDzsUh+WmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:19:03.831193Z"},"content_sha256":"be2fdb8c622da90125e25d53759c622668ed3b21be606067ad2f689f454b922a","schema_version":"1.0","event_id":"sha256:be2fdb8c622da90125e25d53759c622668ed3b21be606067ad2f689f454b922a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/bundle.json","state_url":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/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":"2026-06-01T13:19:03Z","links":{"resolver":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q","bundle":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/bundle.json","state":"https://pith.science/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEWHQTK6LBOPX62UK6O2C4MO2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CEWHQTK6LBOPX62UK6O2C4MO2Q","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":"82a7126fc6257406a39dbd8a5b0153b2b1dd2ddc026f2d64fded601e6bfa288f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-09T15:18:53Z","title_canon_sha256":"3219151239fee2b5d573c05edadde527b784d240afab3267d3a3db08df282099"},"schema_version":"1.0","source":{"id":"1906.03656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03656","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03656v1","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03656","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"CEWHQTK6LBOP","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"CEWHQTK6LBOPX62U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"CEWHQTK6","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:be2fdb8c622da90125e25d53759c622668ed3b21be606067ad2f689f454b922a","target":"graph","created_at":"2026-05-17T23:43:45Z","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"},"paper":{"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","authors_text":"Mohit Iyyer, Tu Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-09T15:18:53Z","title":"Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03656","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:d582dc018cafc9403a666babe96b0ea0d7cdb9931371f753f0e81d72324e12f1","target":"record","created_at":"2026-05-17T23:43:45Z","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":"82a7126fc6257406a39dbd8a5b0153b2b1dd2ddc026f2d64fded601e6bfa288f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-09T15:18:53Z","title_canon_sha256":"3219151239fee2b5d573c05edadde527b784d240afab3267d3a3db08df282099"},"schema_version":"1.0","source":{"id":"1906.03656","kind":"arxiv","version":1}},"canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"112c784d5e585cfbfb54579da1718ed403ef065c4fd2519a968db261e1146cfc","first_computed_at":"2026-05-17T23:43:45.474212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:45.474212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0rynu7iFwj9EngRrKynOT21UNg+T8VHh6+HDhBAt00DT/uv/R2RtT/aI2yJcI7BYmotsMZvTvlxbFqNADMlQBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:45.474868Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d582dc018cafc9403a666babe96b0ea0d7cdb9931371f753f0e81d72324e12f1","sha256:be2fdb8c622da90125e25d53759c622668ed3b21be606067ad2f689f454b922a"],"state_sha256":"b065df0a5d35b2046904e3802f43cfa00283c0247760f1ffce02a6dfa8903a02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbjA68FAKXsnpRgkOl984K8eeIsuTbVgtV9u7KQY8ndEz/saMF86bAH3BGjhQpTtPdge8TdIP5SJVQvF5LwmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T13:19:03.833622Z","bundle_sha256":"7faeb184af06d1ca1f34c36c333cee179df0401be830c33e09261df6b3a957d3"}}