{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:1997:YBRNLPISUK3ZONQZEZ6XWM645P","short_pith_number":"pith:YBRNLPIS","canonical_record":{"source":{"id":"cmp-lg/9702009","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1997-02-12T16:30:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5e27fcf1996875b7d97af77ce6ba93a73b3cd691ce05a99de630cd2963fc89d","abstract_canon_sha256":"1ef76d822a9ee191ca9c367e5fccb9c763edb96b8999bcab92af6a5a2188af70"},"schema_version":"1.0"},"canonical_sha256":"c062d5bd12a2b7973619267d7b33dcebc4a5f749a4b0e3cfe0434a0315e1627b","source":{"kind":"arxiv","id":"cmp-lg/9702009","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9702009","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9702009v1","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9702009","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"YBRNLPISUK3Z","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"YBRNLPISUK3ZONQZ","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"YBRNLPIS","created_at":"2026-07-04T15:08:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:1997:YBRNLPISUK3ZONQZEZ6XWM645P","target":"record","payload":{"canonical_record":{"source":{"id":"cmp-lg/9702009","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1997-02-12T16:30:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5e27fcf1996875b7d97af77ce6ba93a73b3cd691ce05a99de630cd2963fc89d","abstract_canon_sha256":"1ef76d822a9ee191ca9c367e5fccb9c763edb96b8999bcab92af6a5a2188af70"},"schema_version":"1.0"},"canonical_sha256":"c062d5bd12a2b7973619267d7b33dcebc4a5f749a4b0e3cfe0434a0315e1627b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:08:30.321716Z","signature_b64":"aWgYduZ1kNaOXvm74zg3E/ECkNFBZYmB75VujApQRzpa9+a6wIavLPOwHEa0yH3JjSTXPTk4We1NzCpypfkUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c062d5bd12a2b7973619267d7b33dcebc4a5f749a4b0e3cfe0434a0315e1627b","last_reissued_at":"2026-07-04T15:08:30.321356Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:08:30.321356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cmp-lg/9702009","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":"2026-07-04T15:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZuWXPaJV0R+Xsbt03iFI3zzb6JVrWKvv3iL3gFfwChyaan9YiaaKNp/VyMsLABSvgwm1JhJG2jl7sj4zfPf/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:26.364431Z"},"content_sha256":"e47535a6fca3abee89404f8f31ddfb26fe84f77eeb4c63bb5903d0a9731082e8","schema_version":"1.0","event_id":"sha256:e47535a6fca3abee89404f8f31ddfb26fe84f77eeb4c63bb5903d0a9731082e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:1997:YBRNLPISUK3ZONQZEZ6XWM645P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Statistical Parsing of Noun Phrases for Document Indexing","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Chengxiang Zhai (Carnegie Mellon University)","submitted_at":"1997-02-12T16:30:14Z","abstract_excerpt":"Information Retrieval (IR) is an important application area of Natural Language Processing (NLP) where one encounters the genuine challenge of processing large quantities of unrestricted natural language text. While much effort has been made to apply NLP techniques to IR, very few NLP techniques have been evaluated on a document collection larger than several megabytes. Many NLP techniques are simply not efficient enough, and not robust enough, to handle a large amount of text. This paper proposes a new probabilistic model for noun phrase parsing, and reports on the application of such a parsi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9702009","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/cmp-lg/9702009/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":"2026-07-04T15:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SUlr+IdsHxwht5yBGA97q0D43e4OW7ZpppMOHNZ9F1EBP7DVCDdQqYcxt9wHpF5FKb4BceA+fyYcYrxKzSlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:26.364924Z"},"content_sha256":"274505609e3ffbad968017687c5a891ef39fc467c3018706c00801aa9320236d","schema_version":"1.0","event_id":"sha256:274505609e3ffbad968017687c5a891ef39fc467c3018706c00801aa9320236d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBRNLPISUK3ZONQZEZ6XWM645P/bundle.json","state_url":"https://pith.science/pith/YBRNLPISUK3ZONQZEZ6XWM645P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBRNLPISUK3ZONQZEZ6XWM645P/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":"2026-08-09T11:20:26Z","links":{"resolver":"https://pith.science/pith/YBRNLPISUK3ZONQZEZ6XWM645P","bundle":"https://pith.science/pith/YBRNLPISUK3ZONQZEZ6XWM645P/bundle.json","state":"https://pith.science/pith/YBRNLPISUK3ZONQZEZ6XWM645P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBRNLPISUK3ZONQZEZ6XWM645P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1997:YBRNLPISUK3ZONQZEZ6XWM645P","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":"1ef76d822a9ee191ca9c367e5fccb9c763edb96b8999bcab92af6a5a2188af70","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1997-02-12T16:30:14Z","title_canon_sha256":"c5e27fcf1996875b7d97af77ce6ba93a73b3cd691ce05a99de630cd2963fc89d"},"schema_version":"1.0","source":{"id":"cmp-lg/9702009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9702009","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9702009v1","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9702009","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"YBRNLPISUK3Z","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"YBRNLPISUK3ZONQZ","created_at":"2026-07-04T15:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"YBRNLPIS","created_at":"2026-07-04T15:08:30Z"}],"graph_snapshots":[{"event_id":"sha256:274505609e3ffbad968017687c5a891ef39fc467c3018706c00801aa9320236d","target":"graph","created_at":"2026-07-04T15:08:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/cmp-lg/9702009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information Retrieval (IR) is an important application area of Natural Language Processing (NLP) where one encounters the genuine challenge of processing large quantities of unrestricted natural language text. While much effort has been made to apply NLP techniques to IR, very few NLP techniques have been evaluated on a document collection larger than several megabytes. Many NLP techniques are simply not efficient enough, and not robust enough, to handle a large amount of text. This paper proposes a new probabilistic model for noun phrase parsing, and reports on the application of such a parsi","authors_text":"Chengxiang Zhai (Carnegie Mellon University)","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1997-02-12T16:30:14Z","title":"Fast Statistical Parsing of Noun Phrases for Document Indexing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9702009","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:e47535a6fca3abee89404f8f31ddfb26fe84f77eeb4c63bb5903d0a9731082e8","target":"record","created_at":"2026-07-04T15:08:30Z","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":"1ef76d822a9ee191ca9c367e5fccb9c763edb96b8999bcab92af6a5a2188af70","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1997-02-12T16:30:14Z","title_canon_sha256":"c5e27fcf1996875b7d97af77ce6ba93a73b3cd691ce05a99de630cd2963fc89d"},"schema_version":"1.0","source":{"id":"cmp-lg/9702009","kind":"arxiv","version":1}},"canonical_sha256":"c062d5bd12a2b7973619267d7b33dcebc4a5f749a4b0e3cfe0434a0315e1627b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c062d5bd12a2b7973619267d7b33dcebc4a5f749a4b0e3cfe0434a0315e1627b","first_computed_at":"2026-07-04T15:08:30.321356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T15:08:30.321356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aWgYduZ1kNaOXvm74zg3E/ECkNFBZYmB75VujApQRzpa9+a6wIavLPOwHEa0yH3JjSTXPTk4We1NzCpypfkUDw==","signature_status":"signed_v1","signed_at":"2026-07-04T15:08:30.321716Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9702009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e47535a6fca3abee89404f8f31ddfb26fe84f77eeb4c63bb5903d0a9731082e8","sha256:274505609e3ffbad968017687c5a891ef39fc467c3018706c00801aa9320236d"],"state_sha256":"b583dc944e7ef3377c8eaa26c4927e6f29e15a9ce6ad32cff147d68ed69297e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6P75/TN9Rr58xh5uy2Nrh6WSJK9nYudCj1wRWF+eVY7WkxzK7t7wCtv8MAiv2wx+0XdxouyqY1T6961HENKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:26.369162Z","bundle_sha256":"ef350d779893345ba4cc8ed5940b4394f667eeb31d0e49c00a930a51a2ca1011"}}