{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:O7RG6ZGLN65SWJHY352MOIAT7X","short_pith_number":"pith:O7RG6ZGL","canonical_record":{"source":{"id":"1512.01639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:55:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"deb7b52325a720e789354a1ef2b00488f1551d06c7df811f272b94e659e8a7eb","abstract_canon_sha256":"4d83868e77ae7adb71bc75f0ea7645d9d860c9963c42b11b730ba13b2f50cbb6"},"schema_version":"1.0"},"canonical_sha256":"77e26f64cb6fbb2b24f8df74c72013fdfa4728722a7b0a999bbc77062d291de7","source":{"kind":"arxiv","id":"1512.01639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01639","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01639v1","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01639","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"O7RG6ZGLN65S","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"O7RG6ZGLN65SWJHY","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"O7RG6ZGL","created_at":"2026-05-18T12:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:O7RG6ZGLN65SWJHY352MOIAT7X","target":"record","payload":{"canonical_record":{"source":{"id":"1512.01639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:55:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"deb7b52325a720e789354a1ef2b00488f1551d06c7df811f272b94e659e8a7eb","abstract_canon_sha256":"4d83868e77ae7adb71bc75f0ea7645d9d860c9963c42b11b730ba13b2f50cbb6"},"schema_version":"1.0"},"canonical_sha256":"77e26f64cb6fbb2b24f8df74c72013fdfa4728722a7b0a999bbc77062d291de7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:10.747689Z","signature_b64":"o3UXyKWZEYXTAXMG2TAuMjRAgvh3ghDB3asf2CIVPzTo/e6que4mwrhI30nW0+y7ee+EUTZigb/+cGb0cqz/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e26f64cb6fbb2b24f8df74c72013fdfa4728722a7b0a999bbc77062d291de7","last_reissued_at":"2026-05-18T01:25:10.747146Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:10.747146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.01639","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EbIXnT/3ikpW+BotPmdTfwVylHKCcnmRvgPWFoWzjofZOJdwMjf1H33M+w9DVAZkXOJ+JQj2gS9KJFStTRncBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:47:12.469777Z"},"content_sha256":"96e3e850d7d38b13b7fb0063b3a7130353c5bc4f436b332eeaa4dcac805af498","schema_version":"1.0","event_id":"sha256:96e3e850d7d38b13b7fb0063b3a7130353c5bc4f436b332eeaa4dcac805af498"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:O7RG6ZGLN65SWJHY352MOIAT7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PJAIT Systems for the IWSLT 2015 Evaluation Campaign Enhanced by Comparable Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-12-05T08:55:31Z","abstract_excerpt":"In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training settings for each language pair, and obtained comparable corpora for our SMT systems. Innovative tools and data adaptation techniques were employed. The TED parallel text corpora for the IWSLT 2015 evaluation campaign were used to train language models, and to develop, tune, and test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01639","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WO2+vmu8phoz1T4mmKBYTPaolXDwkWYOeehgltk5yzrIQpZo4Md57dy9Uh9+OOB9GEb5qvp9jFP1R3T8QYCEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:47:12.470346Z"},"content_sha256":"bc0c3ce8cef0b3d17aeaac17975bcb7fab18fed27f4470b436df70d121b09f55","schema_version":"1.0","event_id":"sha256:bc0c3ce8cef0b3d17aeaac17975bcb7fab18fed27f4470b436df70d121b09f55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7RG6ZGLN65SWJHY352MOIAT7X/bundle.json","state_url":"https://pith.science/pith/O7RG6ZGLN65SWJHY352MOIAT7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7RG6ZGLN65SWJHY352MOIAT7X/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":"2026-05-25T09:47:12Z","links":{"resolver":"https://pith.science/pith/O7RG6ZGLN65SWJHY352MOIAT7X","bundle":"https://pith.science/pith/O7RG6ZGLN65SWJHY352MOIAT7X/bundle.json","state":"https://pith.science/pith/O7RG6ZGLN65SWJHY352MOIAT7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7RG6ZGLN65SWJHY352MOIAT7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:O7RG6ZGLN65SWJHY352MOIAT7X","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":"4d83868e77ae7adb71bc75f0ea7645d9d860c9963c42b11b730ba13b2f50cbb6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:55:31Z","title_canon_sha256":"deb7b52325a720e789354a1ef2b00488f1551d06c7df811f272b94e659e8a7eb"},"schema_version":"1.0","source":{"id":"1512.01639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01639","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01639v1","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01639","created_at":"2026-05-18T01:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"O7RG6ZGLN65S","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"O7RG6ZGLN65SWJHY","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"O7RG6ZGL","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:bc0c3ce8cef0b3d17aeaac17975bcb7fab18fed27f4470b436df70d121b09f55","target":"graph","created_at":"2026-05-18T01:25:10Z","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":"In this paper, we attempt to improve Statistical Machine Translation (SMT) systems on a very diverse set of language pairs (in both directions): Czech - English, Vietnamese - English, French - English and German - English. To accomplish this, we performed translation model training, created adaptations of training settings for each language pair, and obtained comparable corpora for our SMT systems. Innovative tools and data adaptation techniques were employed. The TED parallel text corpora for the IWSLT 2015 evaluation campaign were used to train language models, and to develop, tune, and test","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:55:31Z","title":"PJAIT Systems for the IWSLT 2015 Evaluation Campaign Enhanced by Comparable Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01639","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":"sha256:96e3e850d7d38b13b7fb0063b3a7130353c5bc4f436b332eeaa4dcac805af498","target":"record","created_at":"2026-05-18T01:25:10Z","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":"4d83868e77ae7adb71bc75f0ea7645d9d860c9963c42b11b730ba13b2f50cbb6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:55:31Z","title_canon_sha256":"deb7b52325a720e789354a1ef2b00488f1551d06c7df811f272b94e659e8a7eb"},"schema_version":"1.0","source":{"id":"1512.01639","kind":"arxiv","version":1}},"canonical_sha256":"77e26f64cb6fbb2b24f8df74c72013fdfa4728722a7b0a999bbc77062d291de7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77e26f64cb6fbb2b24f8df74c72013fdfa4728722a7b0a999bbc77062d291de7","first_computed_at":"2026-05-18T01:25:10.747146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:10.747146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o3UXyKWZEYXTAXMG2TAuMjRAgvh3ghDB3asf2CIVPzTo/e6que4mwrhI30nW0+y7ee+EUTZigb/+cGb0cqz/BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:10.747689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96e3e850d7d38b13b7fb0063b3a7130353c5bc4f436b332eeaa4dcac805af498","sha256:bc0c3ce8cef0b3d17aeaac17975bcb7fab18fed27f4470b436df70d121b09f55"],"state_sha256":"578f60ff047f25043071860c07a09372a7b3d8b3ca1e73c2222cc4546d3c0e8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCCuCs1OiFibahC+az+DRJ+mcTJdrvXcdKArRzJ2x+MkljaXRWCDEYf0HmUCf0ZwJ13vsFbbJl2BTvtZGXUgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:47:12.474007Z","bundle_sha256":"add97a1860d2446d1d6d8eeed819cda9ee781ff52ae7d54a2c8405c1e93f3ebf"}}