{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EZR5OEVSUEDAHBS6GHHIBX6YUF","short_pith_number":"pith:EZR5OEVS","canonical_record":{"source":{"id":"1805.12503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-31T14:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"57e0b37f3255d92fe837a180d086c67d867766bc83464e6bb15be89908d01f32","abstract_canon_sha256":"523d958c8f97c374d73346ea02333b0964dda8520309819bddccfe798b6a7b86"},"schema_version":"1.0"},"canonical_sha256":"2663d712b2a10603865e31ce80dfd8a17cc8ff8c271a7965cc250e85c2f86bec","source":{"kind":"arxiv","id":"1805.12503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12503","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12503v1","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12503","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"EZR5OEVSUEDA","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EZR5OEVSUEDAHBS6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EZR5OEVS","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EZR5OEVSUEDAHBS6GHHIBX6YUF","target":"record","payload":{"canonical_record":{"source":{"id":"1805.12503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-31T14:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"57e0b37f3255d92fe837a180d086c67d867766bc83464e6bb15be89908d01f32","abstract_canon_sha256":"523d958c8f97c374d73346ea02333b0964dda8520309819bddccfe798b6a7b86"},"schema_version":"1.0"},"canonical_sha256":"2663d712b2a10603865e31ce80dfd8a17cc8ff8c271a7965cc250e85c2f86bec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:30.031204Z","signature_b64":"TlLO5zIryhnGUonGOgkjZwcl2aa2qQShjajNAiaN1re0xSAbpZy9YhPVIWiFAdsfxADmkwqQENOTEce6Val5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2663d712b2a10603865e31ce80dfd8a17cc8ff8c271a7965cc250e85c2f86bec","last_reissued_at":"2026-05-18T00:14:30.030475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:30.030475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.12503","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":"2026-05-18T00:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fx4nLZU+z96hm0OHK6RGQO+syrLaMe95fMf6H7CiveFGk6uOJBdkFwLQ1ItNGrmffJOrsAoSaiaBhyBp1JxyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:15:31.606727Z"},"content_sha256":"8cb6d6144cdb58ead270874451f23caaae0c92dbf5622dbbadde743aeab113aa","schema_version":"1.0","event_id":"sha256:8cb6d6144cdb58ead270874451f23caaae0c92dbf5622dbbadde743aeab113aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EZR5OEVSUEDAHBS6GHHIBX6YUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Study of Deterministic Regular Expressions from Large-scale XML and Schema Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chunmei Dong, Haiming Chen, Xiaoying Mou, Xinyu Chu, Yeting Li","submitted_at":"2018-05-31T14:56:02Z","abstract_excerpt":"Regular expressions are a fundamental concept in computer science and widely used in various applications. In this paper we focused on deterministic regular expressions (DREs). Considering that researchers didn't have large datasets as evidence before, we first harvested a large corpus of real data from the Web then conducted a practical study to investigate the usage of DREs. One feature of our work is that the data set is sufficiently large compared with previous work, which is obtained using several data collection strategies we proposed. The results show more than 98\\% of expressions in Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12503","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":"2026-05-18T00:14:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVkMT3L2O8WqkiYjIqVjf+ueSiVqlpR3OUmmuifs2r+BYZ9f0LLcKBxsRPQAOqRrKttC2GJ+yLe5JmFgzZLSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:15:31.607460Z"},"content_sha256":"73a55411fc89488b6f206790e4d2e3b6ef96d93a991b683ccd088c06d9dea146","schema_version":"1.0","event_id":"sha256:73a55411fc89488b6f206790e4d2e3b6ef96d93a991b683ccd088c06d9dea146"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/bundle.json","state_url":"https://pith.science/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/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":"2026-06-10T18:15:31Z","links":{"resolver":"https://pith.science/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF","bundle":"https://pith.science/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/bundle.json","state":"https://pith.science/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZR5OEVSUEDAHBS6GHHIBX6YUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EZR5OEVSUEDAHBS6GHHIBX6YUF","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":"523d958c8f97c374d73346ea02333b0964dda8520309819bddccfe798b6a7b86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-31T14:56:02Z","title_canon_sha256":"57e0b37f3255d92fe837a180d086c67d867766bc83464e6bb15be89908d01f32"},"schema_version":"1.0","source":{"id":"1805.12503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12503","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12503v1","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12503","created_at":"2026-05-18T00:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"EZR5OEVSUEDA","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EZR5OEVSUEDAHBS6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EZR5OEVS","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:73a55411fc89488b6f206790e4d2e3b6ef96d93a991b683ccd088c06d9dea146","target":"graph","created_at":"2026-05-18T00:14:30Z","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":"Regular expressions are a fundamental concept in computer science and widely used in various applications. In this paper we focused on deterministic regular expressions (DREs). Considering that researchers didn't have large datasets as evidence before, we first harvested a large corpus of real data from the Web then conducted a practical study to investigate the usage of DREs. One feature of our work is that the data set is sufficiently large compared with previous work, which is obtained using several data collection strategies we proposed. The results show more than 98\\% of expressions in Re","authors_text":"Chunmei Dong, Haiming Chen, Xiaoying Mou, Xinyu Chu, Yeting Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-31T14:56:02Z","title":"Practical Study of Deterministic Regular Expressions from Large-scale XML and Schema Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12503","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":"sha256:8cb6d6144cdb58ead270874451f23caaae0c92dbf5622dbbadde743aeab113aa","target":"record","created_at":"2026-05-18T00:14:30Z","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":"523d958c8f97c374d73346ea02333b0964dda8520309819bddccfe798b6a7b86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-05-31T14:56:02Z","title_canon_sha256":"57e0b37f3255d92fe837a180d086c67d867766bc83464e6bb15be89908d01f32"},"schema_version":"1.0","source":{"id":"1805.12503","kind":"arxiv","version":1}},"canonical_sha256":"2663d712b2a10603865e31ce80dfd8a17cc8ff8c271a7965cc250e85c2f86bec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2663d712b2a10603865e31ce80dfd8a17cc8ff8c271a7965cc250e85c2f86bec","first_computed_at":"2026-05-18T00:14:30.030475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:30.030475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlLO5zIryhnGUonGOgkjZwcl2aa2qQShjajNAiaN1re0xSAbpZy9YhPVIWiFAdsfxADmkwqQENOTEce6Val5Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:30.031204Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.12503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cb6d6144cdb58ead270874451f23caaae0c92dbf5622dbbadde743aeab113aa","sha256:73a55411fc89488b6f206790e4d2e3b6ef96d93a991b683ccd088c06d9dea146"],"state_sha256":"9e9818247df4c11beb64eb1a53338fe8fe17300971d2e4a05998b2deb37d020a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FNWDtWd8hL3Wdfrm2ZEirYwTZ8LaK780jI6himWUpzmmCYT5iBoU35WUpW9oA9WYnWszSFGFSqFystkhCVoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T18:15:31.611711Z","bundle_sha256":"337871ecd863b88a71335f617951cd4072e4ec0a93569db5225f01c57c3a0ccd"}}