{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:US7BEDUNSD6IBHR5EH6WFENRL7","short_pith_number":"pith:US7BEDUN","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"},"canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","source":{"kind":"arxiv","id":"1303.0407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.0407","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"1303.0407v1","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.0407","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"US7BEDUNSD6I","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_16","alias_value":"US7BEDUNSD6IBHR5","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_8","alias_value":"US7BEDUN","created_at":"2026-05-18T12:28:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:US7BEDUNSD6IBHR5EH6WFENRL7","target":"record","payload":{"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"},"canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","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"},"source_kind":"arxiv","source_id":"1303.0407","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":"2026-05-18T03:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hnj/MpqCT3Lf0biwqpYngzJ3zjbHfHggUcks8tSvirLFNA6H4vkkx28nEYnci5HC7GLBm3nyp/0/dXA8jRhQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:23.304225Z"},"content_sha256":"e35cec0433d0fa5ee2c8337375b93e018bc5e3c565453e81683cc6e346189a9d","schema_version":"1.0","event_id":"sha256:e35cec0433d0fa5ee2c8337375b93e018bc5e3c565453e81683cc6e346189a9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:US7BEDUNSD6IBHR5EH6WFENRL7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BpF0AspRy+tFnO/9YIOfKA0SE5HQ+MiuMdS2FsPEupen1ShWowbrHkoU8Ait1xwbf1auC67hceguvoIkV5pLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:23.304992Z"},"content_sha256":"11b7bd9eb99c9ac503a1ad2bc0021d23f80ac82fe1cdc66236a21bc686953b93","schema_version":"1.0","event_id":"sha256:11b7bd9eb99c9ac503a1ad2bc0021d23f80ac82fe1cdc66236a21bc686953b93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/bundle.json","state_url":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/US7BEDUNSD6IBHR5EH6WFENRL7/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":"2026-05-28T23:39:23Z","links":{"resolver":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7","bundle":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/bundle.json","state":"https://pith.science/pith/US7BEDUNSD6IBHR5EH6WFENRL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/US7BEDUNSD6IBHR5EH6WFENRL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:US7BEDUNSD6IBHR5EH6WFENRL7","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":"a2fe6ee68c178062b44fee871b37d9c8a4651e944cff776bbcafc9b762bee4a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-03-02T17:43:38Z","title_canon_sha256":"9055487075ee4e4883276b7414c652f55e2d1fc52dcb47dd3ce2372eba7d0fec"},"schema_version":"1.0","source":{"id":"1303.0407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.0407","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"1303.0407v1","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.0407","created_at":"2026-05-18T03:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"US7BEDUNSD6I","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_16","alias_value":"US7BEDUNSD6IBHR5","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_8","alias_value":"US7BEDUN","created_at":"2026-05-18T12:28:02Z"}],"graph_snapshots":[{"event_id":"sha256:11b7bd9eb99c9ac503a1ad2bc0021d23f80ac82fe1cdc66236a21bc686953b93","target":"graph","created_at":"2026-05-18T03:31:56Z","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":"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","authors_text":"Ahmad Al Badawi, Qasem Abu Al-Haija","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-03-02T17:43:38Z","title":"IRS for Computer Character Sequences Filtration: a new software tool and algorithm to support the IRS at tokenization process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.0407","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:e35cec0433d0fa5ee2c8337375b93e018bc5e3c565453e81683cc6e346189a9d","target":"record","created_at":"2026-05-18T03:31:56Z","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":"a2fe6ee68c178062b44fee871b37d9c8a4651e944cff776bbcafc9b762bee4a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-03-02T17:43:38Z","title_canon_sha256":"9055487075ee4e4883276b7414c652f55e2d1fc52dcb47dd3ce2372eba7d0fec"},"schema_version":"1.0","source":{"id":"1303.0407","kind":"arxiv","version":1}},"canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4be120e8d90fc809e3d21fd6291b15ff6ac816addde98c0f43061b737f2f46d","first_computed_at":"2026-05-18T03:31:56.189626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:31:56.189626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qIvvHPgrTZMANGTX0G1V2TKGkF0Lth4QpP8YB5Utm0Vp8WCHfTGeL2Qk8Re0DrEer4zBdaq9lp6Ja5JgkNP8Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:31:56.190197Z","signed_message":"canonical_sha256_bytes"},"source_id":"1303.0407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e35cec0433d0fa5ee2c8337375b93e018bc5e3c565453e81683cc6e346189a9d","sha256:11b7bd9eb99c9ac503a1ad2bc0021d23f80ac82fe1cdc66236a21bc686953b93"],"state_sha256":"fff3560467144e6c3bbb7d5af2aeec818ced8c422ffff852a05b36db1c2d6ff5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Np3gutZG3p6vFtRW5K0TbmrJIz9UMDaJAQPybvDsKu5ZmHCFoFgHlBSI5kIUh/0ft4FxZRqahH8tNLUbnX/iCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:39:23.308706Z","bundle_sha256":"c211b99becc4a0a9de751c4f26c11cdf56a7dbe68f68b7e2b890149e3819f605"}}