{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:I43RKPCO2CYVYWVQJIKVLJUNJJ","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":"6e998bef53c708b6b6ac97a4b6ac539640a2156f5563d30ecdcbaccbac53d441","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T07:02:49Z","title_canon_sha256":"f4366393e847b7909331889c83e4e72551f5e63c55a77c6ddc67c3e2363d2455"},"schema_version":"1.0","source":{"id":"1508.02142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02142","created_at":"2026-05-18T01:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02142v1","created_at":"2026-05-18T01:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02142","created_at":"2026-05-18T01:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"I43RKPCO2CYV","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"I43RKPCO2CYVYWVQ","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"I43RKPCO","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:16789c8017901f823354a23922e4788e76c2f0ccd02a6771ff142cd8973154e6","target":"graph","created_at":"2026-05-18T01:35:34Z","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":"Orthographic similarities across languages provide a strong signal for probabilistic decipherment, especially for closely related language pairs. The existing decipherment models, however, are not well-suited for exploiting these orthographic similarities. We propose a log-linear model with latent variables that incorporates orthographic similarity features. Maximum likelihood training is computationally expensive for the proposed log-linear model. To address this challenge, we perform approximate inference via MCMC sampling and contrastive divergence. Our results show that the proposed log-li","authors_text":"Daniel Gildea, Iftekhar Naim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T07:02:49Z","title":"Feature-based Decipherment for Large Vocabulary Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02142","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":"sha256:8a5474515ea3d12ba2efa20f1eb2aaed107498d0b4069d387527456bdb46111d","target":"record","created_at":"2026-05-18T01:35:34Z","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":"6e998bef53c708b6b6ac97a4b6ac539640a2156f5563d30ecdcbaccbac53d441","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T07:02:49Z","title_canon_sha256":"f4366393e847b7909331889c83e4e72551f5e63c55a77c6ddc67c3e2363d2455"},"schema_version":"1.0","source":{"id":"1508.02142","kind":"arxiv","version":1}},"canonical_sha256":"4737153c4ed0b15c5ab04a1555a68d4a5902f67ddb4fabb03bfecf13470779a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4737153c4ed0b15c5ab04a1555a68d4a5902f67ddb4fabb03bfecf13470779a8","first_computed_at":"2026-05-18T01:35:34.075605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:34.075605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AP1xmOxNNqRGbdV60Lkm8GmSWyH4zcOT+5nisVYaOYGs0n3mIvtf2Ur1xSJRsPyxpBpB9xiOOMFuL6fImCnpDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:34.076252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.02142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a5474515ea3d12ba2efa20f1eb2aaed107498d0b4069d387527456bdb46111d","sha256:16789c8017901f823354a23922e4788e76c2f0ccd02a6771ff142cd8973154e6"],"state_sha256":"62f07c4b9403f95b73beb60b3fb681c2408a33e496f97ccb06e242734c303575"}