{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KPO2SXRUZTQZ4PPWNRQ5KFFCJE","short_pith_number":"pith:KPO2SXRU","canonical_record":{"source":{"id":"2110.01295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T10:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"7c7876d5a4e14c37c3e534fb6fdef90e02d339dc4e0e9c1e5885b027c9c3ea72","abstract_canon_sha256":"007963e8d547b8046df88c6147ebba47265f2f15dd8c35d2494ee26e75124836"},"schema_version":"1.0"},"canonical_sha256":"53dda95e34cce19e3df66c61d514a2490c29720984bbf4239ae08eb86c4bd6fa","source":{"kind":"arxiv","id":"2110.01295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01295","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01295v1","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01295","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"KPO2SXRUZTQZ","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"KPO2SXRUZTQZ4PPW","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"KPO2SXRU","created_at":"2026-07-05T03:19:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KPO2SXRUZTQZ4PPWNRQ5KFFCJE","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T10:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"7c7876d5a4e14c37c3e534fb6fdef90e02d339dc4e0e9c1e5885b027c9c3ea72","abstract_canon_sha256":"007963e8d547b8046df88c6147ebba47265f2f15dd8c35d2494ee26e75124836"},"schema_version":"1.0"},"canonical_sha256":"53dda95e34cce19e3df66c61d514a2490c29720984bbf4239ae08eb86c4bd6fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:54.124017Z","signature_b64":"Bav/miNLflUf5+cprOoj8jDRTUlBaYpuAf67BtpMmyJJALdCc6A8E3x3gTA1bkHNSO4/EM02BvvrQFQsG3ghCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53dda95e34cce19e3df66c61d514a2490c29720984bbf4239ae08eb86c4bd6fa","last_reissued_at":"2026-07-05T03:19:54.123597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:54.123597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01295","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":"2026-07-05T03:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPVWXDlGPzaNNdq5ShqJx2FsXVcAtX5Usdz+Y0ygKgmnNH51GUqCRu/zWHkwQXaYaThZo82PG3rlcaEWNWxqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:05:59.325355Z"},"content_sha256":"09d450831f21a38a919be8134d09c9f7bf4747b572a93eec2b84be1fc851bd7f","schema_version":"1.0","event_id":"sha256:09d450831f21a38a919be8134d09c9f7bf4747b572a93eec2b84be1fc851bd7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KPO2SXRUZTQZ4PPWNRQ5KFFCJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alasdair Gray, Bimal Kumar, Farhad Sadeghineko, Ioannis Konstas, Richard Watson, Ruben Kruiper","submitted_at":"2021-10-04T10:00:22Z","abstract_excerpt":"Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01295","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/2110.01295/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":"2026-07-05T03:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zg8GQ2Juz3uQHC9jfjgVaFw/yiQ9WoBneh1tHGbocqfKR7KQEI3eXZuEE0yockGiG3UWgiR2+jFfRwfgxEVwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:05:59.325944Z"},"content_sha256":"ee5c4b5645771dc7ca8ef0133cd475d21e6ff3950d3e7348e4f667c8cbda82b7","schema_version":"1.0","event_id":"sha256:ee5c4b5645771dc7ca8ef0133cd475d21e6ff3950d3e7348e4f667c8cbda82b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/bundle.json","state_url":"https://pith.science/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/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":"2026-08-21T14:05:59Z","links":{"resolver":"https://pith.science/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE","bundle":"https://pith.science/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/bundle.json","state":"https://pith.science/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPO2SXRUZTQZ4PPWNRQ5KFFCJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KPO2SXRUZTQZ4PPWNRQ5KFFCJE","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":"007963e8d547b8046df88c6147ebba47265f2f15dd8c35d2494ee26e75124836","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T10:00:22Z","title_canon_sha256":"7c7876d5a4e14c37c3e534fb6fdef90e02d339dc4e0e9c1e5885b027c9c3ea72"},"schema_version":"1.0","source":{"id":"2110.01295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01295","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01295v1","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01295","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"KPO2SXRUZTQZ","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"KPO2SXRUZTQZ4PPW","created_at":"2026-07-05T03:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"KPO2SXRU","created_at":"2026-07-05T03:19:54Z"}],"graph_snapshots":[{"event_id":"sha256:ee5c4b5645771dc7ca8ef0133cd475d21e6ff3950d3e7348e4f667c8cbda82b7","target":"graph","created_at":"2026-07-05T03:19:54Z","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/2110.01295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a ","authors_text":"Alasdair Gray, Bimal Kumar, Farhad Sadeghineko, Ioannis Konstas, Richard Watson, Ruben Kruiper","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T10:00:22Z","title":"SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01295","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":"sha256:09d450831f21a38a919be8134d09c9f7bf4747b572a93eec2b84be1fc851bd7f","target":"record","created_at":"2026-07-05T03:19:54Z","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":"007963e8d547b8046df88c6147ebba47265f2f15dd8c35d2494ee26e75124836","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-04T10:00:22Z","title_canon_sha256":"7c7876d5a4e14c37c3e534fb6fdef90e02d339dc4e0e9c1e5885b027c9c3ea72"},"schema_version":"1.0","source":{"id":"2110.01295","kind":"arxiv","version":1}},"canonical_sha256":"53dda95e34cce19e3df66c61d514a2490c29720984bbf4239ae08eb86c4bd6fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53dda95e34cce19e3df66c61d514a2490c29720984bbf4239ae08eb86c4bd6fa","first_computed_at":"2026-07-05T03:19:54.123597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:54.123597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bav/miNLflUf5+cprOoj8jDRTUlBaYpuAf67BtpMmyJJALdCc6A8E3x3gTA1bkHNSO4/EM02BvvrQFQsG3ghCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:54.124017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09d450831f21a38a919be8134d09c9f7bf4747b572a93eec2b84be1fc851bd7f","sha256:ee5c4b5645771dc7ca8ef0133cd475d21e6ff3950d3e7348e4f667c8cbda82b7"],"state_sha256":"80d1e56861de14ef5ad44563720c22ceb2874987f59a14c1faca8df5cb6c54ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJJSyboskqL7mAinzeAJtykLZjR8TSOiVEXXZm5AX5CXSEBwFL5u8mDyhoiZZk/uIPTaCxOWnXrdLpUr7jh1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:05:59.330045Z","bundle_sha256":"40e6a24eb4215a0c5ab9bed878f6d4ab3f9c38f3e6913637fe065aad2b8a89e5"}}