{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EK4RFGTHLYATT56ZEHL3LPJYEF","short_pith_number":"pith:EK4RFGTH","canonical_record":{"source":{"id":"1810.08237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T18:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"b1359624ab6948ac925ea2f41c2ffb59ef33c5624a356c511662b28cf99c0675","abstract_canon_sha256":"31867cdb5f7d5550c61461a1c304e31b913ddc1354eb85b29c94e3b9ce306e7e"},"schema_version":"1.0"},"canonical_sha256":"22b9129a675e0139f7d921d7b5bd3821637687077796022404655464f0dda5e3","source":{"kind":"arxiv","id":"1810.08237","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08237","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08237v2","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08237","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"EK4RFGTHLYAT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EK4RFGTHLYATT56Z","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EK4RFGTH","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EK4RFGTHLYATT56ZEHL3LPJYEF","target":"record","payload":{"canonical_record":{"source":{"id":"1810.08237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T18:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"b1359624ab6948ac925ea2f41c2ffb59ef33c5624a356c511662b28cf99c0675","abstract_canon_sha256":"31867cdb5f7d5550c61461a1c304e31b913ddc1354eb85b29c94e3b9ce306e7e"},"schema_version":"1.0"},"canonical_sha256":"22b9129a675e0139f7d921d7b5bd3821637687077796022404655464f0dda5e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:37.062619Z","signature_b64":"CyUD098jjIIZN2dsHa5NbCp8mA/yzCqpNwllXRja3UxBQjuUsUgBcDiAkNPQSQYjodfvx81v2A+IX4l2PvfqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22b9129a675e0139f7d921d7b5bd3821637687077796022404655464f0dda5e3","last_reissued_at":"2026-05-17T23:39:37.062062Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:37.062062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.08237","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLA/e9SjDonXZVseAoBoyrsxCDUlYW7OV0uxTb3S/1PEFmNxTd77bMqWsnk0QrBSr6Wgej3xPYyfGVAC5Pj3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:41:53.447642Z"},"content_sha256":"c588606515d456a429b91780838a0bb1cf89ef71f002562125dec2ba51dfc991","schema_version":"1.0","event_id":"sha256:c588606515d456a429b91780838a0bb1cf89ef71f002562125dec2ba51dfc991"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EK4RFGTHLYATT56ZEHL3LPJYEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-scale Hierarchical Alignment for Data-driven Text Rewriting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nikola I. Nikolov, Richard H.R. Hahnloser","submitted_at":"2018-10-18T18:51:43Z","abstract_excerpt":"We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08237","kind":"arxiv","version":2},"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":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ckRlAdHZPmTRAcS13vl/wrKAIXWkmYf6/xfMad/3ekMcv8CtYct4YFkVAs3KA9oJP2qMqGyCUoZdnn7DpGXEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:41:53.448248Z"},"content_sha256":"58e9e713a2dab56e73484c698fe3d4d2fd8befc38968602db67605877157eb80","schema_version":"1.0","event_id":"sha256:58e9e713a2dab56e73484c698fe3d4d2fd8befc38968602db67605877157eb80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/bundle.json","state_url":"https://pith.science/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/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":"2026-06-09T05:41:53Z","links":{"resolver":"https://pith.science/pith/EK4RFGTHLYATT56ZEHL3LPJYEF","bundle":"https://pith.science/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/bundle.json","state":"https://pith.science/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EK4RFGTHLYATT56ZEHL3LPJYEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EK4RFGTHLYATT56ZEHL3LPJYEF","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":"31867cdb5f7d5550c61461a1c304e31b913ddc1354eb85b29c94e3b9ce306e7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T18:51:43Z","title_canon_sha256":"b1359624ab6948ac925ea2f41c2ffb59ef33c5624a356c511662b28cf99c0675"},"schema_version":"1.0","source":{"id":"1810.08237","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08237","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08237v2","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08237","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"EK4RFGTHLYAT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EK4RFGTHLYATT56Z","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EK4RFGTH","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:58e9e713a2dab56e73484c698fe3d4d2fd8befc38968602db67605877157eb80","target":"graph","created_at":"2026-05-17T23:39:37Z","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":"We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only s","authors_text":"Nikola I. Nikolov, Richard H.R. Hahnloser","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T18:51:43Z","title":"Large-scale Hierarchical Alignment for Data-driven Text Rewriting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08237","kind":"arxiv","version":2},"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:c588606515d456a429b91780838a0bb1cf89ef71f002562125dec2ba51dfc991","target":"record","created_at":"2026-05-17T23:39:37Z","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":"31867cdb5f7d5550c61461a1c304e31b913ddc1354eb85b29c94e3b9ce306e7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-18T18:51:43Z","title_canon_sha256":"b1359624ab6948ac925ea2f41c2ffb59ef33c5624a356c511662b28cf99c0675"},"schema_version":"1.0","source":{"id":"1810.08237","kind":"arxiv","version":2}},"canonical_sha256":"22b9129a675e0139f7d921d7b5bd3821637687077796022404655464f0dda5e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22b9129a675e0139f7d921d7b5bd3821637687077796022404655464f0dda5e3","first_computed_at":"2026-05-17T23:39:37.062062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:37.062062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CyUD098jjIIZN2dsHa5NbCp8mA/yzCqpNwllXRja3UxBQjuUsUgBcDiAkNPQSQYjodfvx81v2A+IX4l2PvfqBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:37.062619Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08237","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c588606515d456a429b91780838a0bb1cf89ef71f002562125dec2ba51dfc991","sha256:58e9e713a2dab56e73484c698fe3d4d2fd8befc38968602db67605877157eb80"],"state_sha256":"4d1468ebde09c15e03af9058740ea56600cb2027b775599875f96045c60ff46c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J46yltffuK35p7k5tYfdMi1q8hjx09Hb/Sw1PdJR1Tvk5Rd21J46xNgGqI7j2AqzV3pET2a+NzWnzQeBj1Q+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T05:41:53.451954Z","bundle_sha256":"a1e750ff3dd18b1f7e12e05161ae5276e00f62824cc0cbaaa3457ddd107265f0"}}