{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AFXWJWL5T4OCADXGLIGYCKIHT6","short_pith_number":"pith:AFXWJWL5","canonical_record":{"source":{"id":"1709.00541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T07:00:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18d3b0a4d56bdd67bbb493304d6874ff689ac6bd09deea973e2e59a13a2df35d","abstract_canon_sha256":"b03ad05edd0da634a1886a8af1629d55047d56cf36697102e6c189966d016231"},"schema_version":"1.0"},"canonical_sha256":"016f64d97d9f1c200ee65a0d8129079f865b600dd1ad07363618bed6fce06f30","source":{"kind":"arxiv","id":"1709.00541","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00541","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00541v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00541","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"AFXWJWL5T4OC","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AFXWJWL5T4OCADXG","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AFXWJWL5","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AFXWJWL5T4OCADXGLIGYCKIHT6","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T07:00:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18d3b0a4d56bdd67bbb493304d6874ff689ac6bd09deea973e2e59a13a2df35d","abstract_canon_sha256":"b03ad05edd0da634a1886a8af1629d55047d56cf36697102e6c189966d016231"},"schema_version":"1.0"},"canonical_sha256":"016f64d97d9f1c200ee65a0d8129079f865b600dd1ad07363618bed6fce06f30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:07.756472Z","signature_b64":"J/RxLtkJf0JFustnyUEbmeHColC3QtGnpFutSjhjHCBwP63NJSJn6Pbj437IqIwUCYxEmefsfSssB0FjPdVICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"016f64d97d9f1c200ee65a0d8129079f865b600dd1ad07363618bed6fce06f30","last_reissued_at":"2026-05-18T00:36:07.755716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:07.755716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00541","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":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIFLezI5ezpOjR/eXiHfjrg3t3aCfil0oAYfvPTkRtEcMGnJsPwusbwHVZSYA4B1ge/A5TjyAL0z16DfDOMIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:34:35.287938Z"},"content_sha256":"0b707a7e08086dbfd6b374a31ae247a4ae8227f8f44c1aa6b58237ab621a6e95","schema_version":"1.0","event_id":"sha256:0b707a7e08086dbfd6b374a31ae247a4ae8227f8f44c1aa6b58237ab621a6e95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AFXWJWL5T4OCADXGLIGYCKIHT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Patterns versus Characters in Subword-aware Neural Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Rustem Takhanov, Zhenisbek Assylbekov","submitted_at":"2017-09-02T07:00:22Z","abstract_excerpt":"Words in some natural languages can have a composite structure. Elements of this structure include the root (that could also be composite), prefixes and suffixes with which various nuances and relations to other words can be expressed. Thus, in order to build a proper word representation one must take into account its internal structure. From a corpus of texts we extract a set of frequent subwords and from the latter set we select patterns, i.e. subwords which encapsulate information on character $n$-gram regularities. The selection is made using the pattern-based Conditional Random Field mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00541","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":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wC4NHLN48bokAX34hOuHTNNVzZnTeogb6125YYneV/YDPj5pN8to5C7o0bJKItRSFD4XsZofbqNoWrfYE30AAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:34:35.288276Z"},"content_sha256":"b1512ed69a79f2803d7c0e5e06a8f453bbe4da4ac20d43934ff8c805c396a798","schema_version":"1.0","event_id":"sha256:b1512ed69a79f2803d7c0e5e06a8f453bbe4da4ac20d43934ff8c805c396a798"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/bundle.json","state_url":"https://pith.science/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/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":"2026-06-28T04:34:35Z","links":{"resolver":"https://pith.science/pith/AFXWJWL5T4OCADXGLIGYCKIHT6","bundle":"https://pith.science/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/bundle.json","state":"https://pith.science/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AFXWJWL5T4OCADXGLIGYCKIHT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AFXWJWL5T4OCADXGLIGYCKIHT6","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":"b03ad05edd0da634a1886a8af1629d55047d56cf36697102e6c189966d016231","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T07:00:22Z","title_canon_sha256":"18d3b0a4d56bdd67bbb493304d6874ff689ac6bd09deea973e2e59a13a2df35d"},"schema_version":"1.0","source":{"id":"1709.00541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00541","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00541v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00541","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"AFXWJWL5T4OC","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AFXWJWL5T4OCADXG","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AFXWJWL5","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b1512ed69a79f2803d7c0e5e06a8f453bbe4da4ac20d43934ff8c805c396a798","target":"graph","created_at":"2026-05-18T00:36:07Z","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":"Words in some natural languages can have a composite structure. Elements of this structure include the root (that could also be composite), prefixes and suffixes with which various nuances and relations to other words can be expressed. Thus, in order to build a proper word representation one must take into account its internal structure. From a corpus of texts we extract a set of frequent subwords and from the latter set we select patterns, i.e. subwords which encapsulate information on character $n$-gram regularities. The selection is made using the pattern-based Conditional Random Field mode","authors_text":"Rustem Takhanov, Zhenisbek Assylbekov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T07:00:22Z","title":"Patterns versus Characters in Subword-aware Neural Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00541","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":"sha256:0b707a7e08086dbfd6b374a31ae247a4ae8227f8f44c1aa6b58237ab621a6e95","target":"record","created_at":"2026-05-18T00:36:07Z","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":"b03ad05edd0da634a1886a8af1629d55047d56cf36697102e6c189966d016231","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T07:00:22Z","title_canon_sha256":"18d3b0a4d56bdd67bbb493304d6874ff689ac6bd09deea973e2e59a13a2df35d"},"schema_version":"1.0","source":{"id":"1709.00541","kind":"arxiv","version":1}},"canonical_sha256":"016f64d97d9f1c200ee65a0d8129079f865b600dd1ad07363618bed6fce06f30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"016f64d97d9f1c200ee65a0d8129079f865b600dd1ad07363618bed6fce06f30","first_computed_at":"2026-05-18T00:36:07.755716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:07.755716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J/RxLtkJf0JFustnyUEbmeHColC3QtGnpFutSjhjHCBwP63NJSJn6Pbj437IqIwUCYxEmefsfSssB0FjPdVICg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:07.756472Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b707a7e08086dbfd6b374a31ae247a4ae8227f8f44c1aa6b58237ab621a6e95","sha256:b1512ed69a79f2803d7c0e5e06a8f453bbe4da4ac20d43934ff8c805c396a798"],"state_sha256":"f0052a0da3f8412f6c9dd85781063e6f0a2917435188e773d37530d0df25ed0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x8Qaau9gmaSe3XnC4j21+XHzZ93rMBNhEc+L7vQqqPB8g6yDeIC5BIRA5gWeqfB+iERNWwt04S4rXBrBaO76CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:34:35.290196Z","bundle_sha256":"b215253a180ffee9abc6a327fd1a45d61b4c2eff68dec800255cea7b94e8065a"}}