{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VWRWXVMU4PIMYHDZAQRJMRFZT3","short_pith_number":"pith:VWRWXVMU","canonical_record":{"source":{"id":"1808.03840","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T17:31:15Z","cross_cats_sorted":[],"title_canon_sha256":"f2ba3599dcabfbfb53eb526d7201affd596476dad46040ea3e775f664cc16827","abstract_canon_sha256":"66d03a115999fea02ba30815afc280f8b0476d6cb8ab1be356a2ddbe6172d228"},"schema_version":"1.0"},"canonical_sha256":"ada36bd594e3d0cc1c7904229644b99ed91aee8ab470802c2f8dd74047173bab","source":{"kind":"arxiv","id":"1808.03840","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03840","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03840v4","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03840","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"VWRWXVMU4PIM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VWRWXVMU4PIMYHDZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VWRWXVMU","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VWRWXVMU4PIMYHDZAQRJMRFZT3","target":"record","payload":{"canonical_record":{"source":{"id":"1808.03840","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T17:31:15Z","cross_cats_sorted":[],"title_canon_sha256":"f2ba3599dcabfbfb53eb526d7201affd596476dad46040ea3e775f664cc16827","abstract_canon_sha256":"66d03a115999fea02ba30815afc280f8b0476d6cb8ab1be356a2ddbe6172d228"},"schema_version":"1.0"},"canonical_sha256":"ada36bd594e3d0cc1c7904229644b99ed91aee8ab470802c2f8dd74047173bab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:23.183241Z","signature_b64":"Juv1ypCz8DfGK4J2aqCDZ8a0LoOJglrLrO8mWFGkSYLqyYFmkYRGQoV/m8+Kg2GbN+LHSsOuq7DwNUTeO0gXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ada36bd594e3d0cc1c7904229644b99ed91aee8ab470802c2f8dd74047173bab","last_reissued_at":"2026-05-18T00:07:23.182758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:23.182758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.03840","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7PSZdNx72bvIshsenH6j+TfdbPtkxwEaPSS8rci0tRVDIf9599AqEl+DaPJZ4Pc1wwwYxINW7HKEppoNEjFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:23:11.178261Z"},"content_sha256":"37112cbfa76db07ff53742876f56429bd65ae4ce1324495e9e8a1ec9d2e8a655","schema_version":"1.0","event_id":"sha256:37112cbfa76db07ff53742876f56429bd65ae4ce1324495e9e8a1ec9d2e8a655"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VWRWXVMU4PIMYHDZAQRJMRFZT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fake Sentence Detection as a Training Task for Sentence Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heeyoung Kwon, Minh Hoai, Niranjan Balasubramanian, Viresh Ranjan","submitted_at":"2018-08-11T17:31:15Z","abstract_excerpt":"Sentence encoders are typically trained on language modeling tasks with large unlabeled datasets. While these encoders achieve state-of-the-art results on many sentence-level tasks, they are difficult to train with long training cycles. We introduce fake sentence detection as a new training task for learning sentence encoders. We automatically generate fake sentences by corrupting original sentences from a source collection and train the encoders to produce representations that are effective at detecting fake sentences. This binary classification task turns to be quite efficient for training s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03840","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+5XWx58FuZRKf0YyGEXoHizJjTlM6JU9gq/rAJ9mqsGOS/ubK/9ZkX/2mNBZx6DM3wKywIw9l7vRGysUOmwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:23:11.178705Z"},"content_sha256":"e255a294fd76f3db95fbbdcb6ef3adf1e9f21ee32ac068ff0f71cf5029073253","schema_version":"1.0","event_id":"sha256:e255a294fd76f3db95fbbdcb6ef3adf1e9f21ee32ac068ff0f71cf5029073253"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/bundle.json","state_url":"https://pith.science/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/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":"2026-06-01T22:23:11Z","links":{"resolver":"https://pith.science/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3","bundle":"https://pith.science/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/bundle.json","state":"https://pith.science/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWRWXVMU4PIMYHDZAQRJMRFZT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VWRWXVMU4PIMYHDZAQRJMRFZT3","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":"66d03a115999fea02ba30815afc280f8b0476d6cb8ab1be356a2ddbe6172d228","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T17:31:15Z","title_canon_sha256":"f2ba3599dcabfbfb53eb526d7201affd596476dad46040ea3e775f664cc16827"},"schema_version":"1.0","source":{"id":"1808.03840","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.03840","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1808.03840v4","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03840","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"VWRWXVMU4PIM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VWRWXVMU4PIMYHDZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VWRWXVMU","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:e255a294fd76f3db95fbbdcb6ef3adf1e9f21ee32ac068ff0f71cf5029073253","target":"graph","created_at":"2026-05-18T00:07:23Z","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":"Sentence encoders are typically trained on language modeling tasks with large unlabeled datasets. While these encoders achieve state-of-the-art results on many sentence-level tasks, they are difficult to train with long training cycles. We introduce fake sentence detection as a new training task for learning sentence encoders. We automatically generate fake sentences by corrupting original sentences from a source collection and train the encoders to produce representations that are effective at detecting fake sentences. This binary classification task turns to be quite efficient for training s","authors_text":"Heeyoung Kwon, Minh Hoai, Niranjan Balasubramanian, Viresh Ranjan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T17:31:15Z","title":"Fake Sentence Detection as a Training Task for Sentence Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03840","kind":"arxiv","version":4},"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":"sha256:37112cbfa76db07ff53742876f56429bd65ae4ce1324495e9e8a1ec9d2e8a655","target":"record","created_at":"2026-05-18T00:07:23Z","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":"66d03a115999fea02ba30815afc280f8b0476d6cb8ab1be356a2ddbe6172d228","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T17:31:15Z","title_canon_sha256":"f2ba3599dcabfbfb53eb526d7201affd596476dad46040ea3e775f664cc16827"},"schema_version":"1.0","source":{"id":"1808.03840","kind":"arxiv","version":4}},"canonical_sha256":"ada36bd594e3d0cc1c7904229644b99ed91aee8ab470802c2f8dd74047173bab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ada36bd594e3d0cc1c7904229644b99ed91aee8ab470802c2f8dd74047173bab","first_computed_at":"2026-05-18T00:07:23.182758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:23.182758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Juv1ypCz8DfGK4J2aqCDZ8a0LoOJglrLrO8mWFGkSYLqyYFmkYRGQoV/m8+Kg2GbN+LHSsOuq7DwNUTeO0gXBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:23.183241Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.03840","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37112cbfa76db07ff53742876f56429bd65ae4ce1324495e9e8a1ec9d2e8a655","sha256:e255a294fd76f3db95fbbdcb6ef3adf1e9f21ee32ac068ff0f71cf5029073253"],"state_sha256":"f288903cd46f1f314ec0a19a218d864f6ab05849247f94201618c0ce3ced2fbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//EjwAiENn26MquBA63yKismZexxOWDuYXGZ0xrem1/TpUZK+cBIRxE5qMmmj54SiDNxbqouSm2mm8DnKeeCDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:23:11.180826Z","bundle_sha256":"c42ab944201a877cb7035e3057df691b86f1cb967be3e54118f63e292f3da949"}}