{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ODQ72NXPV73F4ZHFJUMQRGBWVN","short_pith_number":"pith:ODQ72NXP","schema_version":"1.0","canonical_sha256":"70e1fd36efaff65e64e54d19089836ab51f8f569cf62cbf189827e2ddb491776","source":{"kind":"arxiv","id":"2205.12527","version":1},"attestation_state":"computed","paper":{"title":"Segmenting Numerical Substitution Ciphers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Nada Aldarrab","submitted_at":"2022-05-25T06:45:59Z","abstract_excerpt":"Deciphering historical substitution ciphers is a challenging problem. Example problems that have been previously studied include detecting cipher type, detecting plaintext language, and acquiring the substitution key for segmented ciphers. However, attacking unsegmented, space-free ciphers is still a challenging task. Segmentation (i.e. finding substitution units) is the first step towards cracking those ciphers. In this work, we propose the first automatic methods to segment those ciphers using Byte Pair Encoding (BPE) and unigram language models. Our methods achieve an average segmentation e"},"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":"2205.12527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:45:59Z","cross_cats_sorted":[],"title_canon_sha256":"68913e4dfc4865cac36ee77be0997d7b14f8c443e36168d3bd013c763e91474d","abstract_canon_sha256":"49da24a3d9fdb6f5d9cce9dca7c040e13c311be2a0cfa57a3be2cf70b332800f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:26.656832Z","signature_b64":"dWxD0ST03qfaovT4czHC/xYVmFpiGB4gknIpyT4tI72n5iGLm1WUEnWUNXXAqevfpV+b2OgB/xVCwv7bc6NOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70e1fd36efaff65e64e54d19089836ab51f8f569cf62cbf189827e2ddb491776","last_reissued_at":"2026-07-05T04:26:26.656406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:26.656406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segmenting Numerical Substitution Ciphers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Nada Aldarrab","submitted_at":"2022-05-25T06:45:59Z","abstract_excerpt":"Deciphering historical substitution ciphers is a challenging problem. Example problems that have been previously studied include detecting cipher type, detecting plaintext language, and acquiring the substitution key for segmented ciphers. However, attacking unsegmented, space-free ciphers is still a challenging task. Segmentation (i.e. finding substitution units) is the first step towards cracking those ciphers. In this work, we propose the first automatic methods to segment those ciphers using Byte Pair Encoding (BPE) and unigram language models. Our methods achieve an average segmentation e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12527","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/2205.12527/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.12527","created_at":"2026-07-05T04:26:26.656473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12527v1","created_at":"2026-07-05T04:26:26.656473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12527","created_at":"2026-07-05T04:26:26.656473+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODQ72NXPV73F","created_at":"2026-07-05T04:26:26.656473+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODQ72NXPV73F4ZHF","created_at":"2026-07-05T04:26:26.656473+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODQ72NXP","created_at":"2026-07-05T04:26:26.656473+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/ODQ72NXPV73F4ZHFJUMQRGBWVN","json":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN.json","graph_json":"https://pith.science/api/pith-number/ODQ72NXPV73F4ZHFJUMQRGBWVN/graph.json","events_json":"https://pith.science/api/pith-number/ODQ72NXPV73F4ZHFJUMQRGBWVN/events.json","paper":"https://pith.science/paper/ODQ72NXP"},"agent_actions":{"view_html":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN","download_json":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN.json","view_paper":"https://pith.science/paper/ODQ72NXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12527&json=true","fetch_graph":"https://pith.science/api/pith-number/ODQ72NXPV73F4ZHFJUMQRGBWVN/graph.json","fetch_events":"https://pith.science/api/pith-number/ODQ72NXPV73F4ZHFJUMQRGBWVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN/action/storage_attestation","attest_author":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN/action/author_attestation","sign_citation":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN/action/citation_signature","submit_replication":"https://pith.science/pith/ODQ72NXPV73F4ZHFJUMQRGBWVN/action/replication_record"}},"created_at":"2026-07-05T04:26:26.656473+00:00","updated_at":"2026-07-05T04:26:26.656473+00:00"}