{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:1999:RQ5RJIZ5FAZAV6E76O472S2YLQ","short_pith_number":"pith:RQ5RJIZ5","canonical_record":{"source":{"id":"cs/9902001","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"1999-01-31T18:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"133e7930ef3852e99c44b4a6b978e7361231c0eef917f97ddbd4a563e09aacc3","abstract_canon_sha256":"502de2d444c9a915a45cb15c4bf54494fdbcdddcc83da69d47e63dd4da080a8e"},"schema_version":"1.0"},"canonical_sha256":"8c3b14a33d28320af89ff3b9fd4b585c2d93ae1c2024fe51bd417b3bd7309fae","source":{"kind":"arxiv","id":"cs/9902001","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/9902001","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"cs/9902001v1","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/9902001","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"RQ5RJIZ5FAZA","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"RQ5RJIZ5FAZAV6E7","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"RQ5RJIZ5","created_at":"2026-07-04T14:25:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:1999:RQ5RJIZ5FAZAV6E76O472S2YLQ","target":"record","payload":{"canonical_record":{"source":{"id":"cs/9902001","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"1999-01-31T18:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"133e7930ef3852e99c44b4a6b978e7361231c0eef917f97ddbd4a563e09aacc3","abstract_canon_sha256":"502de2d444c9a915a45cb15c4bf54494fdbcdddcc83da69d47e63dd4da080a8e"},"schema_version":"1.0"},"canonical_sha256":"8c3b14a33d28320af89ff3b9fd4b585c2d93ae1c2024fe51bd417b3bd7309fae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:25:09.349659Z","signature_b64":"s7ej3HoPJoABBrvxfTIF8g5WqRdhh5yMfmtL7uVgpjfxzh48+5TjtPlpWyWDeyJ9Fw5DrLxiZ3mL1a0e3OtdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c3b14a33d28320af89ff3b9fd4b585c2d93ae1c2024fe51bd417b3bd7309fae","last_reissued_at":"2026-07-04T14:25:09.349254Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:25:09.349254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cs/9902001","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":"2026-07-04T14:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3rO8Ua3lKA8pAVXCkMAMiW3SKYGD9I+w/sNedu+AVEwDGSjZecxC3MYfdnyJC907s7/UU8j5PzTe0cc3VmWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:43:53.485603Z"},"content_sha256":"8097b8cbe263e173097fde7eb106cc240962bddf4605e516d246ddfd724217e2","schema_version":"1.0","event_id":"sha256:8097b8cbe263e173097fde7eb106cc240962bddf4605e516d246ddfd724217e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:1999:RQ5RJIZ5FAZAV6E76O472S2YLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compacting the Penn Treebank Grammar","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Krotov, Mark Hepple, Robert Gaizauskas, UK), University of Sheffield, Yorick Wilks (Department of Computer Science","submitted_at":"1999-01-31T18:57:45Z","abstract_excerpt":"Treebanks, such as the Penn Treebank (PTB), offer a simple approach to obtaining a broad coverage grammar: one can simply read the grammar off the parse trees in the treebank. While such a grammar is easy to obtain, a square-root rate of growth of the rule set with corpus size suggests that the derived grammar is far from complete and that much more treebanked text would be required to obtain a complete grammar, if one exists at some limit. However, we offer an alternative explanation in terms of the underspecification of structures within the treebank. This hypothesis is explored by applying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/9902001","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/cs/9902001/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":"2026-07-04T14:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+xocSp63xM/3oQGGpmDOQCVzR+Z0szZjy1eVgrh0i4MB/lD2Fp4K+4xHImJMw49OkCPC5RMQsu0VyhR26BgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:43:53.486431Z"},"content_sha256":"b248101c6100f831f4b34200975896c19c7255a1347b2c0505551ba985bd1f97","schema_version":"1.0","event_id":"sha256:b248101c6100f831f4b34200975896c19c7255a1347b2c0505551ba985bd1f97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/bundle.json","state_url":"https://pith.science/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/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":"2026-08-11T03:43:53Z","links":{"resolver":"https://pith.science/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ","bundle":"https://pith.science/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/bundle.json","state":"https://pith.science/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQ5RJIZ5FAZAV6E76O472S2YLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1999:RQ5RJIZ5FAZAV6E76O472S2YLQ","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":"502de2d444c9a915a45cb15c4bf54494fdbcdddcc83da69d47e63dd4da080a8e","cross_cats_sorted":[],"license":"","primary_cat":"cs.CL","submitted_at":"1999-01-31T18:57:45Z","title_canon_sha256":"133e7930ef3852e99c44b4a6b978e7361231c0eef917f97ddbd4a563e09aacc3"},"schema_version":"1.0","source":{"id":"cs/9902001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/9902001","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"cs/9902001v1","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/9902001","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"RQ5RJIZ5FAZA","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"RQ5RJIZ5FAZAV6E7","created_at":"2026-07-04T14:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"RQ5RJIZ5","created_at":"2026-07-04T14:25:09Z"}],"graph_snapshots":[{"event_id":"sha256:b248101c6100f831f4b34200975896c19c7255a1347b2c0505551ba985bd1f97","target":"graph","created_at":"2026-07-04T14:25:09Z","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/cs/9902001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Treebanks, such as the Penn Treebank (PTB), offer a simple approach to obtaining a broad coverage grammar: one can simply read the grammar off the parse trees in the treebank. While such a grammar is easy to obtain, a square-root rate of growth of the rule set with corpus size suggests that the derived grammar is far from complete and that much more treebanked text would be required to obtain a complete grammar, if one exists at some limit. However, we offer an alternative explanation in terms of the underspecification of structures within the treebank. This hypothesis is explored by applying ","authors_text":"Alexander Krotov, Mark Hepple, Robert Gaizauskas, UK), University of Sheffield, Yorick Wilks (Department of Computer Science","cross_cats":[],"headline":"","license":"","primary_cat":"cs.CL","submitted_at":"1999-01-31T18:57:45Z","title":"Compacting the Penn Treebank Grammar"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/9902001","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":"sha256:8097b8cbe263e173097fde7eb106cc240962bddf4605e516d246ddfd724217e2","target":"record","created_at":"2026-07-04T14:25:09Z","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":"502de2d444c9a915a45cb15c4bf54494fdbcdddcc83da69d47e63dd4da080a8e","cross_cats_sorted":[],"license":"","primary_cat":"cs.CL","submitted_at":"1999-01-31T18:57:45Z","title_canon_sha256":"133e7930ef3852e99c44b4a6b978e7361231c0eef917f97ddbd4a563e09aacc3"},"schema_version":"1.0","source":{"id":"cs/9902001","kind":"arxiv","version":1}},"canonical_sha256":"8c3b14a33d28320af89ff3b9fd4b585c2d93ae1c2024fe51bd417b3bd7309fae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c3b14a33d28320af89ff3b9fd4b585c2d93ae1c2024fe51bd417b3bd7309fae","first_computed_at":"2026-07-04T14:25:09.349254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T14:25:09.349254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s7ej3HoPJoABBrvxfTIF8g5WqRdhh5yMfmtL7uVgpjfxzh48+5TjtPlpWyWDeyJ9Fw5DrLxiZ3mL1a0e3OtdBQ==","signature_status":"signed_v1","signed_at":"2026-07-04T14:25:09.349659Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/9902001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8097b8cbe263e173097fde7eb106cc240962bddf4605e516d246ddfd724217e2","sha256:b248101c6100f831f4b34200975896c19c7255a1347b2c0505551ba985bd1f97"],"state_sha256":"cfd8929a927260af133ae706b68322f444d9418a561c019fd8b3d7ba6c820278"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zBQkCfjbcuXX46XcoBg05N7Oa6n7MDVU+QxX0GpwuzRi7v4drZRutJ7abMH8gMwVEzkTULBe7gr3UGisZP7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:43:53.493068Z","bundle_sha256":"7210ec95211c0d3d9c97602a6e153f4903f69b79ba0bd2970a16c59bc110ee3d"}}