{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:VDQUD3TUBTIULJ4IUKMQCZFIJF","short_pith_number":"pith:VDQUD3TU","canonical_record":{"source":{"id":"1401.5698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-15T05:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"b6699eb11bf2c8554849e9b20c74dbd0ea082951da061c5aa4161fc9b90831cc","abstract_canon_sha256":"3e3cec4108957c27030d201cd8d3c74313a10b8d269915144336f0a111445137"},"schema_version":"1.0"},"canonical_sha256":"a8e141ee740cd145a788a2990164a84950321afdb8a4098793fd3c9c0a19584d","source":{"kind":"arxiv","id":"1401.5698","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.5698","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"1401.5698v1","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.5698","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"VDQUD3TUBTIU","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"VDQUD3TUBTIULJ4I","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"VDQUD3TU","created_at":"2026-05-18T12:28:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:VDQUD3TUBTIULJ4IUKMQCZFIJF","target":"record","payload":{"canonical_record":{"source":{"id":"1401.5698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-15T05:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"b6699eb11bf2c8554849e9b20c74dbd0ea082951da061c5aa4161fc9b90831cc","abstract_canon_sha256":"3e3cec4108957c27030d201cd8d3c74313a10b8d269915144336f0a111445137"},"schema_version":"1.0"},"canonical_sha256":"a8e141ee740cd145a788a2990164a84950321afdb8a4098793fd3c9c0a19584d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:01:24.929660Z","signature_b64":"W4ZwaPq4/ggsYuh9b6e35UkFwHXBQLgjZidRwtKjJRRxTh9k4KtvPBo336tiFx6NEBiX0DSBgHeynJNsBXP2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e141ee740cd145a788a2990164a84950321afdb8a4098793fd3c9c0a19584d","last_reissued_at":"2026-05-18T03:01:24.928982Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:01:24.928982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1401.5698","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":"2026-05-18T03:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bf51w6Ho774D3fkqGd4Kk/Q8bkK9Ss2kb5QDHWQxLeT10sdLCgNfj5jRIOqiUfePxyTfElR+JiFD+Z670btrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:22:01.212540Z"},"content_sha256":"3c152aa53c05b09ad521f92574ccdfa5bca6d66c5a84d6d56d5ec3a5863aec9a","schema_version":"1.0","event_id":"sha256:3c152aa53c05b09ad521f92574ccdfa5bca6d66c5a84d6d56d5ec3a5863aec9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:VDQUD3TUBTIULJ4IUKMQCZFIJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identification of Pleonastic It Using the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Loren Wyard-Scott, Marek Reformat, Petr Musilek, Yifan Li","submitted_at":"2014-01-15T05:11:43Z","abstract_excerpt":"In a significant minority of cases, certain pronouns, especially the pronoun it, can be used without referring to any specific entity. This phenomenon of pleonastic pronoun usage poses serious problems for systems aiming at even a shallow understanding of natural language texts. In this paper, a novel approach is proposed to identify such uses of it: the extrapositional cases are identified using a series of queries against the web, and the cleft cases are identified using a simple set of syntactic rules. The system is evaluated with four sets of news articles containing 679 extrapositional ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.5698","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":"2026-05-18T03:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5QITl7Pjh0nRydsfNC19cIYkEwPaQOUXZhzPSxHiBLVrDud6HSyG/r0zoVVLhSdeWjQlIPLsBSlXFWWoxVnIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:22:01.212889Z"},"content_sha256":"8bbd5104b53708c0cc52a5045d4f8935116f78c96e6f28da38e72a7ff52edc39","schema_version":"1.0","event_id":"sha256:8bbd5104b53708c0cc52a5045d4f8935116f78c96e6f28da38e72a7ff52edc39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/bundle.json","state_url":"https://pith.science/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/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":"2026-06-02T22:22:01Z","links":{"resolver":"https://pith.science/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF","bundle":"https://pith.science/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/bundle.json","state":"https://pith.science/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDQUD3TUBTIULJ4IUKMQCZFIJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:VDQUD3TUBTIULJ4IUKMQCZFIJF","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":"3e3cec4108957c27030d201cd8d3c74313a10b8d269915144336f0a111445137","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-15T05:11:43Z","title_canon_sha256":"b6699eb11bf2c8554849e9b20c74dbd0ea082951da061c5aa4161fc9b90831cc"},"schema_version":"1.0","source":{"id":"1401.5698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.5698","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"1401.5698v1","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.5698","created_at":"2026-05-18T03:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"VDQUD3TUBTIU","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"VDQUD3TUBTIULJ4I","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"VDQUD3TU","created_at":"2026-05-18T12:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:8bbd5104b53708c0cc52a5045d4f8935116f78c96e6f28da38e72a7ff52edc39","target":"graph","created_at":"2026-05-18T03:01:24Z","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":"In a significant minority of cases, certain pronouns, especially the pronoun it, can be used without referring to any specific entity. This phenomenon of pleonastic pronoun usage poses serious problems for systems aiming at even a shallow understanding of natural language texts. In this paper, a novel approach is proposed to identify such uses of it: the extrapositional cases are identified using a series of queries against the web, and the cleft cases are identified using a simple set of syntactic rules. The system is evaluated with four sets of news articles containing 679 extrapositional ca","authors_text":"Loren Wyard-Scott, Marek Reformat, Petr Musilek, Yifan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-15T05:11:43Z","title":"Identification of Pleonastic It Using the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.5698","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":"sha256:3c152aa53c05b09ad521f92574ccdfa5bca6d66c5a84d6d56d5ec3a5863aec9a","target":"record","created_at":"2026-05-18T03:01:24Z","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":"3e3cec4108957c27030d201cd8d3c74313a10b8d269915144336f0a111445137","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-15T05:11:43Z","title_canon_sha256":"b6699eb11bf2c8554849e9b20c74dbd0ea082951da061c5aa4161fc9b90831cc"},"schema_version":"1.0","source":{"id":"1401.5698","kind":"arxiv","version":1}},"canonical_sha256":"a8e141ee740cd145a788a2990164a84950321afdb8a4098793fd3c9c0a19584d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8e141ee740cd145a788a2990164a84950321afdb8a4098793fd3c9c0a19584d","first_computed_at":"2026-05-18T03:01:24.928982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:01:24.928982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W4ZwaPq4/ggsYuh9b6e35UkFwHXBQLgjZidRwtKjJRRxTh9k4KtvPBo336tiFx6NEBiX0DSBgHeynJNsBXP2AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:01:24.929660Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.5698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c152aa53c05b09ad521f92574ccdfa5bca6d66c5a84d6d56d5ec3a5863aec9a","sha256:8bbd5104b53708c0cc52a5045d4f8935116f78c96e6f28da38e72a7ff52edc39"],"state_sha256":"a15a7cf7969c2bd08421fbbaf043d588f4e94f1a430accad54d39f031d8b123c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oS9LfA1kuCpNnknhNLu1RHpG/HB4cHUGwKePz3Oqt4fwlltYZCPiAP9bXWPT+Z8hCYYStEH/589jV4a2GMrNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:22:01.215166Z","bundle_sha256":"3b98934881aa8f4f6bda1a14eac233e0715c0d5771a06c98ecea27171492cd89"}}