{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:I43RKPCO2CYVYWVQJIKVLJUNJJ","short_pith_number":"pith:I43RKPCO","schema_version":"1.0","canonical_sha256":"4737153c4ed0b15c5ab04a1555a68d4a5902f67ddb4fabb03bfecf13470779a8","source":{"kind":"arxiv","id":"1508.02142","version":1},"attestation_state":"computed","paper":{"title":"Feature-based Decipherment for Large Vocabulary Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Gildea, Iftekhar Naim","submitted_at":"2015-08-10T07:02:49Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1508.02142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T07:02:49Z","cross_cats_sorted":[],"title_canon_sha256":"f4366393e847b7909331889c83e4e72551f5e63c55a77c6ddc67c3e2363d2455","abstract_canon_sha256":"6e998bef53c708b6b6ac97a4b6ac539640a2156f5563d30ecdcbaccbac53d441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:34.076252Z","signature_b64":"AP1xmOxNNqRGbdV60Lkm8GmSWyH4zcOT+5nisVYaOYGs0n3mIvtf2Ur1xSJRsPyxpBpB9xiOOMFuL6fImCnpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4737153c4ed0b15c5ab04a1555a68d4a5902f67ddb4fabb03bfecf13470779a8","last_reissued_at":"2026-05-18T01:35:34.075605Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:34.075605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature-based Decipherment for Large Vocabulary Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Gildea, Iftekhar Naim","submitted_at":"2015-08-10T07:02:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02142","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1508.02142","created_at":"2026-05-18T01:35:34.075712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.02142v1","created_at":"2026-05-18T01:35:34.075712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02142","created_at":"2026-05-18T01:35:34.075712+00:00"},{"alias_kind":"pith_short_12","alias_value":"I43RKPCO2CYV","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"I43RKPCO2CYVYWVQ","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"I43RKPCO","created_at":"2026-05-18T12:29:25.134429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ","json":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ.json","graph_json":"https://pith.science/api/pith-number/I43RKPCO2CYVYWVQJIKVLJUNJJ/graph.json","events_json":"https://pith.science/api/pith-number/I43RKPCO2CYVYWVQJIKVLJUNJJ/events.json","paper":"https://pith.science/paper/I43RKPCO"},"agent_actions":{"view_html":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ","download_json":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ.json","view_paper":"https://pith.science/paper/I43RKPCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.02142&json=true","fetch_graph":"https://pith.science/api/pith-number/I43RKPCO2CYVYWVQJIKVLJUNJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I43RKPCO2CYVYWVQJIKVLJUNJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ/action/storage_attestation","attest_author":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ/action/author_attestation","sign_citation":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ/action/citation_signature","submit_replication":"https://pith.science/pith/I43RKPCO2CYVYWVQJIKVLJUNJJ/action/replication_record"}},"created_at":"2026-05-18T01:35:34.075712+00:00","updated_at":"2026-05-18T01:35:34.075712+00:00"}