{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:US7BEDUNSD6IBHR5EH6WFENRL7","short_pith_number":"pith:US7BEDUN","schema_version":"1.0","canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","source":{"kind":"arxiv","id":"1303.0407","version":1},"attestation_state":"computed","paper":{"title":"IRS for Computer Character Sequences Filtration: a new software tool and algorithm to support the IRS at tokenization process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ahmad Al Badawi, Qasem Abu Al-Haija","submitted_at":"2013-03-02T17:43:38Z","abstract_excerpt":"Tokenization is the task of chopping it up into pieces, called tokens, perhaps at the same time throwing away certain characters, such as punctuation. A token is an instance of token a sequence of characters in some particular document that are grouped together as a useful semantic unit for processing. New software tool and algorithm to support the IRS at tokenization process are presented. Our proposed tool will filter out the three computer character Sequences: IP-Addresses, Web URLs, Date, and Email Addresses. Our tool will use the pattern matching algorithms and filtration methods. After t"},"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":"1303.0407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-03-02T17:43:38Z","cross_cats_sorted":[],"title_canon_sha256":"9055487075ee4e4883276b7414c652f55e2d1fc52dcb47dd3ce2372eba7d0fec","abstract_canon_sha256":"a2fe6ee68c178062b44fee871b37d9c8a4651e944cff776bbcafc9b762bee4a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:31:56.190197Z","signature_b64":"qIvvHPgrTZMANGTX0G1V2TKGkF0Lth4QpP8YB5Utm0Vp8WCHfTGeL2Qk8Re0DrEer4zBdaq9lp6Ja5JgkNP8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","last_reissued_at":"2026-05-18T03:31:56.189626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:31:56.189626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IRS for Computer Character Sequences Filtration: a new software tool and algorithm to support the IRS at tokenization process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ahmad Al Badawi, Qasem Abu Al-Haija","submitted_at":"2013-03-02T17:43:38Z","abstract_excerpt":"Tokenization is the task of chopping it up into pieces, called tokens, perhaps at the same time throwing away certain characters, such as punctuation. A token is an instance of token a sequence of characters in some particular document that are grouped together as a useful semantic unit for processing. New software tool and algorithm to support the IRS at tokenization process are presented. Our proposed tool will filter out the three computer character Sequences: IP-Addresses, Web URLs, Date, and Email Addresses. Our tool will use the pattern matching algorithms and filtration methods. After t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.0407","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":"1303.0407","created_at":"2026-05-18T03:31:56.189711+00:00"},{"alias_kind":"arxiv_version","alias_value":"1303.0407v1","created_at":"2026-05-18T03:31:56.189711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.0407","created_at":"2026-05-18T03:31:56.189711+00:00"},{"alias_kind":"pith_short_12","alias_value":"US7BEDUNSD6I","created_at":"2026-05-18T12:28:02.375192+00:00"},{"alias_kind":"pith_short_16","alias_value":"US7BEDUNSD6IBHR5","created_at":"2026-05-18T12:28:02.375192+00:00"},{"alias_kind":"pith_short_8","alias_value":"US7BEDUN","created_at":"2026-05-18T12:28:02.375192+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/US7BEDUNSD6IBHR5EH6WFENRL7","json":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7.json","graph_json":"https://pith.science/api/pith-number/US7BEDUNSD6IBHR5EH6WFENRL7/graph.json","events_json":"https://pith.science/api/pith-number/US7BEDUNSD6IBHR5EH6WFENRL7/events.json","paper":"https://pith.science/paper/US7BEDUN"},"agent_actions":{"view_html":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7","download_json":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7.json","view_paper":"https://pith.science/paper/US7BEDUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1303.0407&json=true","fetch_graph":"https://pith.science/api/pith-number/US7BEDUNSD6IBHR5EH6WFENRL7/graph.json","fetch_events":"https://pith.science/api/pith-number/US7BEDUNSD6IBHR5EH6WFENRL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/action/storage_attestation","attest_author":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/action/author_attestation","sign_citation":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/action/citation_signature","submit_replication":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/action/replication_record"}},"created_at":"2026-05-18T03:31:56.189711+00:00","updated_at":"2026-05-18T03:31:56.189711+00:00"}