{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:WXTHGRKFHU7NZQ4WTFSUULV73M","short_pith_number":"pith:WXTHGRKF","canonical_record":{"source":{"id":"1502.07038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-25T03:27:38Z","cross_cats_sorted":[],"title_canon_sha256":"af78dc922f80fdcc99623fd1f7914961204807c1f3f4ffae8192251f2b217fbd","abstract_canon_sha256":"3d392479178732c808ceb71a087172db9559cfd97a4af2a436197b3f7d83094c"},"schema_version":"1.0"},"canonical_sha256":"b5e67345453d3edcc39699654a2ebfdb01492c366fe7a78d698f10a22a8a730d","source":{"kind":"arxiv","id":"1502.07038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.07038","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"1502.07038v1","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.07038","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"WXTHGRKFHU7N","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WXTHGRKFHU7NZQ4W","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WXTHGRKF","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:WXTHGRKFHU7NZQ4WTFSUULV73M","target":"record","payload":{"canonical_record":{"source":{"id":"1502.07038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-25T03:27:38Z","cross_cats_sorted":[],"title_canon_sha256":"af78dc922f80fdcc99623fd1f7914961204807c1f3f4ffae8192251f2b217fbd","abstract_canon_sha256":"3d392479178732c808ceb71a087172db9559cfd97a4af2a436197b3f7d83094c"},"schema_version":"1.0"},"canonical_sha256":"b5e67345453d3edcc39699654a2ebfdb01492c366fe7a78d698f10a22a8a730d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:12.047517Z","signature_b64":"TiTDr/L+jesizPZBu3mdba6tKbn7NgN5hiTSPjjN8OeDIrnLe9LR+6/jGlQJlkfF4E0LlhMDK3wydIJhnCIDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5e67345453d3edcc39699654a2ebfdb01492c366fe7a78d698f10a22a8a730d","last_reissued_at":"2026-05-18T02:26:12.047004Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:12.047004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.07038","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":"2026-05-18T02:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmP8SbOLaxMGYxczjsvGCnm+Ytto6BAfW2qA84SRR8Arsb5EL3AHROQl+xgsRHggZ/zYc4H8fRlyBiNLn/9cCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:41:51.813574Z"},"content_sha256":"638e82a0f4c96d522f3ef43fd2b2850b5d1cf1e97214793f475fc8d8949b107e","schema_version":"1.0","event_id":"sha256:638e82a0f4c96d522f3ef43fd2b2850b5d1cf1e97214793f475fc8d8949b107e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:WXTHGRKFHU7NZQ4WTFSUULV73M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Web-scale Surface and Syntactic n-gram Features for Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominick Ng, James R. Curran, Mohit Bansal","submitted_at":"2015-02-25T03:27:38Z","abstract_excerpt":"We develop novel first- and second-order features for dependency parsing based on the Google Syntactic Ngrams corpus, a collection of subtree counts of parsed sentences from scanned books. We also extend previous work on surface $n$-gram features from Web1T to the Google Books corpus and from first-order to second-order, comparing and analysing performance over newswire and web treebanks.\n  Surface and syntactic $n$-grams both produce substantial and complementary gains in parsing accuracy across domains. Our best system combines the two feature sets, achieving up to 0.8% absolute UAS improvem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.07038","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":"2026-05-18T02:26:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubtXpY3o2PP5YEzgNaUGCX2zYy8srFAHiGoeRcquzoI6Uiy982IiouT8hCtUM49v6EgLQu0UTTrb5VqmX/mxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:41:51.813924Z"},"content_sha256":"113166671949ef7f1a166da35757b7718eba10b94027ba528e5b8b98cb52a3ec","schema_version":"1.0","event_id":"sha256:113166671949ef7f1a166da35757b7718eba10b94027ba528e5b8b98cb52a3ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/bundle.json","state_url":"https://pith.science/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/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":"2026-06-11T12:41:51Z","links":{"resolver":"https://pith.science/pith/WXTHGRKFHU7NZQ4WTFSUULV73M","bundle":"https://pith.science/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/bundle.json","state":"https://pith.science/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXTHGRKFHU7NZQ4WTFSUULV73M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:WXTHGRKFHU7NZQ4WTFSUULV73M","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":"3d392479178732c808ceb71a087172db9559cfd97a4af2a436197b3f7d83094c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-25T03:27:38Z","title_canon_sha256":"af78dc922f80fdcc99623fd1f7914961204807c1f3f4ffae8192251f2b217fbd"},"schema_version":"1.0","source":{"id":"1502.07038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.07038","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"1502.07038v1","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.07038","created_at":"2026-05-18T02:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"WXTHGRKFHU7N","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WXTHGRKFHU7NZQ4W","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WXTHGRKF","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:113166671949ef7f1a166da35757b7718eba10b94027ba528e5b8b98cb52a3ec","target":"graph","created_at":"2026-05-18T02:26:12Z","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":"We develop novel first- and second-order features for dependency parsing based on the Google Syntactic Ngrams corpus, a collection of subtree counts of parsed sentences from scanned books. We also extend previous work on surface $n$-gram features from Web1T to the Google Books corpus and from first-order to second-order, comparing and analysing performance over newswire and web treebanks.\n  Surface and syntactic $n$-grams both produce substantial and complementary gains in parsing accuracy across domains. Our best system combines the two feature sets, achieving up to 0.8% absolute UAS improvem","authors_text":"Dominick Ng, James R. Curran, Mohit Bansal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-25T03:27:38Z","title":"Web-scale Surface and Syntactic n-gram Features for Dependency Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.07038","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":"sha256:638e82a0f4c96d522f3ef43fd2b2850b5d1cf1e97214793f475fc8d8949b107e","target":"record","created_at":"2026-05-18T02:26:12Z","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":"3d392479178732c808ceb71a087172db9559cfd97a4af2a436197b3f7d83094c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-25T03:27:38Z","title_canon_sha256":"af78dc922f80fdcc99623fd1f7914961204807c1f3f4ffae8192251f2b217fbd"},"schema_version":"1.0","source":{"id":"1502.07038","kind":"arxiv","version":1}},"canonical_sha256":"b5e67345453d3edcc39699654a2ebfdb01492c366fe7a78d698f10a22a8a730d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5e67345453d3edcc39699654a2ebfdb01492c366fe7a78d698f10a22a8a730d","first_computed_at":"2026-05-18T02:26:12.047004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:26:12.047004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TiTDr/L+jesizPZBu3mdba6tKbn7NgN5hiTSPjjN8OeDIrnLe9LR+6/jGlQJlkfF4E0LlhMDK3wydIJhnCIDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:26:12.047517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.07038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:638e82a0f4c96d522f3ef43fd2b2850b5d1cf1e97214793f475fc8d8949b107e","sha256:113166671949ef7f1a166da35757b7718eba10b94027ba528e5b8b98cb52a3ec"],"state_sha256":"026aac2ea9d82351803901f4540e0f502f4490450d2df4fe2d3ebd3402a491a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5VY0IU0Kdl2yUoC0vxpxaPdq2+EyQ0fW2VADs3+O+pyL2R/ewAGsCRtpcIrjGUF05NjgAfKihY/CI5MUP5qCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:41:51.816068Z","bundle_sha256":"c823daa5ea59fe583b15b825e120a0745fe9f3599cbd65f3d90a17093df091bf"}}