{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6TCFGKS77P4G45UKDPXAUF5B5C","short_pith_number":"pith:6TCFGKS7","canonical_record":{"source":{"id":"2011.02173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"5faff6659ca4e986ef61dfa6deaa0ad13a4426c303a16b5627a2628918ec7dc1","abstract_canon_sha256":"e2feaf6a5a3b1de118dac42b1c2c286915a6f869b2b9113468bd6c10eb38f6fd"},"schema_version":"1.0"},"canonical_sha256":"f4c4532a5ffbf86e768a1bee0a17a1e8983b1a46f9706f33973cef90283f5ddc","source":{"kind":"arxiv","id":"2011.02173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02173","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02173v1","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02173","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"6TCFGKS77P4G","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"6TCFGKS77P4G45UK","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"6TCFGKS7","created_at":"2026-07-05T01:49:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6TCFGKS77P4G45UKDPXAUF5B5C","target":"record","payload":{"canonical_record":{"source":{"id":"2011.02173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"5faff6659ca4e986ef61dfa6deaa0ad13a4426c303a16b5627a2628918ec7dc1","abstract_canon_sha256":"e2feaf6a5a3b1de118dac42b1c2c286915a6f869b2b9113468bd6c10eb38f6fd"},"schema_version":"1.0"},"canonical_sha256":"f4c4532a5ffbf86e768a1bee0a17a1e8983b1a46f9706f33973cef90283f5ddc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:09.979486Z","signature_b64":"MCPmk5IHEhQAuXJHwXuKcVmUXdAwgDLzTV7YkPyfO+HqUh94FQqr4e+3W8FLhlpboHdqO+2jovvD3F0lm6GzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c4532a5ffbf86e768a1bee0a17a1e8983b1a46f9706f33973cef90283f5ddc","last_reissued_at":"2026-07-05T01:49:09.979063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:09.979063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.02173","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":"2026-07-05T01:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijdGhUX92fHJu7XNuvdpmIh4btAeCBHCpSNmbMOLHg7zF6H/UjUgNqsPAP09krMsBsUM9z3JW+E2j5HFEtdhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:15:45.392550Z"},"content_sha256":"34c247873625e892133711173eae0e719e493841135dbc2a34da1a3cb859fd74","schema_version":"1.0","event_id":"sha256:34c247873625e892133711173eae0e719e493841135dbc2a34da1a3cb859fd74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6TCFGKS77P4G45UKDPXAUF5B5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural text normalization leveraging similarities of strings and sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura, Riku Kawamura, Tatsuya Aoki","submitted_at":"2020-11-04T08:24:05Z","abstract_excerpt":"We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline. Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters. So that the proposed models a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02173","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.02173/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/p7LThOJlXbXG7zyvQoujv5SpmblMUHX0Ie5EphEajzNiQnk2rRyRTBzrLKXpOKA2ausoVQ+fJD3WtzbrXgpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:15:45.393056Z"},"content_sha256":"10300c007bc12fef0cc01a3d32f726a4aa7acffff5674a71328e0a24a72a425b","schema_version":"1.0","event_id":"sha256:10300c007bc12fef0cc01a3d32f726a4aa7acffff5674a71328e0a24a72a425b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TCFGKS77P4G45UKDPXAUF5B5C/bundle.json","state_url":"https://pith.science/pith/6TCFGKS77P4G45UKDPXAUF5B5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TCFGKS77P4G45UKDPXAUF5B5C/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":"2026-08-05T11:15:45Z","links":{"resolver":"https://pith.science/pith/6TCFGKS77P4G45UKDPXAUF5B5C","bundle":"https://pith.science/pith/6TCFGKS77P4G45UKDPXAUF5B5C/bundle.json","state":"https://pith.science/pith/6TCFGKS77P4G45UKDPXAUF5B5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TCFGKS77P4G45UKDPXAUF5B5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6TCFGKS77P4G45UKDPXAUF5B5C","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":"e2feaf6a5a3b1de118dac42b1c2c286915a6f869b2b9113468bd6c10eb38f6fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T08:24:05Z","title_canon_sha256":"5faff6659ca4e986ef61dfa6deaa0ad13a4426c303a16b5627a2628918ec7dc1"},"schema_version":"1.0","source":{"id":"2011.02173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02173","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02173v1","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02173","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"6TCFGKS77P4G","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"6TCFGKS77P4G45UK","created_at":"2026-07-05T01:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"6TCFGKS7","created_at":"2026-07-05T01:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:10300c007bc12fef0cc01a3d32f726a4aa7acffff5674a71328e0a24a72a425b","target":"graph","created_at":"2026-07-05T01:49:09Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.02173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline. Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters. So that the proposed models a","authors_text":"Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura, Riku Kawamura, Tatsuya Aoki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T08:24:05Z","title":"Neural text normalization leveraging similarities of strings and sounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02173","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":"sha256:34c247873625e892133711173eae0e719e493841135dbc2a34da1a3cb859fd74","target":"record","created_at":"2026-07-05T01:49:09Z","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":"e2feaf6a5a3b1de118dac42b1c2c286915a6f869b2b9113468bd6c10eb38f6fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T08:24:05Z","title_canon_sha256":"5faff6659ca4e986ef61dfa6deaa0ad13a4426c303a16b5627a2628918ec7dc1"},"schema_version":"1.0","source":{"id":"2011.02173","kind":"arxiv","version":1}},"canonical_sha256":"f4c4532a5ffbf86e768a1bee0a17a1e8983b1a46f9706f33973cef90283f5ddc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4c4532a5ffbf86e768a1bee0a17a1e8983b1a46f9706f33973cef90283f5ddc","first_computed_at":"2026-07-05T01:49:09.979063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:09.979063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MCPmk5IHEhQAuXJHwXuKcVmUXdAwgDLzTV7YkPyfO+HqUh94FQqr4e+3W8FLhlpboHdqO+2jovvD3F0lm6GzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:09.979486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34c247873625e892133711173eae0e719e493841135dbc2a34da1a3cb859fd74","sha256:10300c007bc12fef0cc01a3d32f726a4aa7acffff5674a71328e0a24a72a425b"],"state_sha256":"209afa11ce7c76cafd5dad9f27bf8358ddc228623490abc67ee43b6ee94f15f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJ+SF4egJ6rtHJbTS43sgTmas9/478lIqe/FeFy1sZVxEW9MeNAnOLiybocAWYUlgXS+Vlg5QtLmpz7GXqFjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:15:45.398354Z","bundle_sha256":"fede09832ae008ec7fd601384c972fabacdc78df8555e686a5d92fba7aa9b6aa"}}