{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KBO3I4AO4LAQGFZNSRG47B5D2G","short_pith_number":"pith:KBO3I4AO","canonical_record":{"source":{"id":"1801.08337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-25T10:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"835b9e232bfff53ed1862f236e9642ebb9e4c99623d25d024d81d4930528c5c6","abstract_canon_sha256":"25d57e648137ae2a77f951cc9598123d74d98badfa6887be4ca4e7d996c08756"},"schema_version":"1.0"},"canonical_sha256":"505db4700ee2c103172d944dcf87a3d184f203128f769868617dbf80293d687c","source":{"kind":"arxiv","id":"1801.08337","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.08337","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"1801.08337v2","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.08337","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"KBO3I4AO4LAQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KBO3I4AO4LAQGFZN","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KBO3I4AO","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KBO3I4AO4LAQGFZNSRG47B5D2G","target":"record","payload":{"canonical_record":{"source":{"id":"1801.08337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-25T10:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"835b9e232bfff53ed1862f236e9642ebb9e4c99623d25d024d81d4930528c5c6","abstract_canon_sha256":"25d57e648137ae2a77f951cc9598123d74d98badfa6887be4ca4e7d996c08756"},"schema_version":"1.0"},"canonical_sha256":"505db4700ee2c103172d944dcf87a3d184f203128f769868617dbf80293d687c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:59.073996Z","signature_b64":"sYukzKJmUd8LIgymKD3do953lPK71SmpDwFBmqU0H0HKyotCbtCPDsXzM3K2OYZ7z5ecGA/efodhQexTyuFQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505db4700ee2c103172d944dcf87a3d184f203128f769868617dbf80293d687c","last_reissued_at":"2026-05-18T00:24:59.073370Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:59.073370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.08337","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":"2026-05-18T00:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1JC0ICZbjK4qRfwYkcjEoRyATCmbnyeqFgGGmZ2ATkcz7TLX0+G5tdHDG9M/yrgq7hLXX2Q3bc2jC2dkAdWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:17:58.306387Z"},"content_sha256":"24abdfb6466166434042c3fc2ace803821328d04965d1204376eb738d11c6a4e","schema_version":"1.0","event_id":"sha256:24abdfb6466166434042c3fc2ace803821328d04965d1204376eb738d11c6a4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KBO3I4AO4LAQGFZNSRG47B5D2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuous Space Reordering Models for Phrase-based MT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahim Dalvi, Nadir Durrani","submitted_at":"2018-01-25T10:17:32Z","abstract_excerpt":"Bilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very small context sizes. This problem has been previously addressed by learning sequences over generalized representations such as POS tags or word clusters. In this paper, we explore an alternative based on neural network models. More concretely we train neuralized versions of lexicalized reordering and the operation sequence models using feed-forward neural network. Our resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.08337","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":"2026-05-18T00:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaogNCqllUTai6CDILsKpiJOXcWiZTyAuyo+H4W04r3tf7BF909Ohvu30gHiYFcO4fDffQb7lGHplTcXOWA2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:17:58.306850Z"},"content_sha256":"db61025c93acebbb3603f11c578acfd4743d06a373d09b3b9a2eb785b33467d5","schema_version":"1.0","event_id":"sha256:db61025c93acebbb3603f11c578acfd4743d06a373d09b3b9a2eb785b33467d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/bundle.json","state_url":"https://pith.science/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/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":"2026-05-31T03:17:58Z","links":{"resolver":"https://pith.science/pith/KBO3I4AO4LAQGFZNSRG47B5D2G","bundle":"https://pith.science/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/bundle.json","state":"https://pith.science/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBO3I4AO4LAQGFZNSRG47B5D2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KBO3I4AO4LAQGFZNSRG47B5D2G","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":"25d57e648137ae2a77f951cc9598123d74d98badfa6887be4ca4e7d996c08756","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-25T10:17:32Z","title_canon_sha256":"835b9e232bfff53ed1862f236e9642ebb9e4c99623d25d024d81d4930528c5c6"},"schema_version":"1.0","source":{"id":"1801.08337","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.08337","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"1801.08337v2","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.08337","created_at":"2026-05-18T00:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"KBO3I4AO4LAQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KBO3I4AO4LAQGFZN","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KBO3I4AO","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:db61025c93acebbb3603f11c578acfd4743d06a373d09b3b9a2eb785b33467d5","target":"graph","created_at":"2026-05-18T00:24:59Z","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":"Bilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very small context sizes. This problem has been previously addressed by learning sequences over generalized representations such as POS tags or word clusters. In this paper, we explore an alternative based on neural network models. More concretely we train neuralized versions of lexicalized reordering and the operation sequence models using feed-forward neural network. Our resul","authors_text":"Fahim Dalvi, Nadir Durrani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-25T10:17:32Z","title":"Continuous Space Reordering Models for Phrase-based MT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.08337","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":"sha256:24abdfb6466166434042c3fc2ace803821328d04965d1204376eb738d11c6a4e","target":"record","created_at":"2026-05-18T00:24:59Z","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":"25d57e648137ae2a77f951cc9598123d74d98badfa6887be4ca4e7d996c08756","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-25T10:17:32Z","title_canon_sha256":"835b9e232bfff53ed1862f236e9642ebb9e4c99623d25d024d81d4930528c5c6"},"schema_version":"1.0","source":{"id":"1801.08337","kind":"arxiv","version":2}},"canonical_sha256":"505db4700ee2c103172d944dcf87a3d184f203128f769868617dbf80293d687c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"505db4700ee2c103172d944dcf87a3d184f203128f769868617dbf80293d687c","first_computed_at":"2026-05-18T00:24:59.073370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:59.073370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sYukzKJmUd8LIgymKD3do953lPK71SmpDwFBmqU0H0HKyotCbtCPDsXzM3K2OYZ7z5ecGA/efodhQexTyuFQDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:59.073996Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.08337","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24abdfb6466166434042c3fc2ace803821328d04965d1204376eb738d11c6a4e","sha256:db61025c93acebbb3603f11c578acfd4743d06a373d09b3b9a2eb785b33467d5"],"state_sha256":"40071396ae287a00fd58c7c4efc76fd12ee2fbfc8c13362f1f1d363ed1e2447d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubWo9/XDFsKT6PbKI7wwGspW/ehsnDhUOIR+DXMOlFSG8ZgS0OL8pT/H3VGJgkznqJ4fcNFqfKNSBqLl6yLUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:17:58.309943Z","bundle_sha256":"3e51dd48459b9e6622007fb6b792cd7144000ecd1558d021585eb6a3ddc5be14"}}