{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5SOKHRM26VFML6YE4IINZSFFDD","short_pith_number":"pith:5SOKHRM2","canonical_record":{"source":{"id":"1705.10814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-30T18:23:18Z","cross_cats_sorted":[],"title_canon_sha256":"f468ddd809ca0ae6adf00f94029c9768d5e95b8f82fdf1600dae172ba0cb6808","abstract_canon_sha256":"b968276d52f94f838b31484584af679c8eee379077e50a4163f1f9833f2cc4ce"},"schema_version":"1.0"},"canonical_sha256":"ec9ca3c59af54ac5fb04e210dcc8a518dae915fba0e085c9aa3d592a213d8204","source":{"kind":"arxiv","id":"1705.10814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10814","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10814v1","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10814","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"5SOKHRM26VFM","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SOKHRM26VFML6YE","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SOKHRM2","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5SOKHRM26VFML6YE4IINZSFFDD","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-30T18:23:18Z","cross_cats_sorted":[],"title_canon_sha256":"f468ddd809ca0ae6adf00f94029c9768d5e95b8f82fdf1600dae172ba0cb6808","abstract_canon_sha256":"b968276d52f94f838b31484584af679c8eee379077e50a4163f1f9833f2cc4ce"},"schema_version":"1.0"},"canonical_sha256":"ec9ca3c59af54ac5fb04e210dcc8a518dae915fba0e085c9aa3d592a213d8204","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:20.169921Z","signature_b64":"dmQhm+/oc65D2wfDJUv4EwFFo10FHtL4WP6YmlxrDTv0+MF09YFNY/cQ5gz2Je7teoEhL4YbMdxtc3iE98NNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec9ca3c59af54ac5fb04e210dcc8a518dae915fba0e085c9aa3d592a213d8204","last_reissued_at":"2026-05-18T00:43:20.169217Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:20.169217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10814","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":"2026-05-18T00:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5XRViOdH7fWtdMLAuNW6ywooyERHnUOuzJSTbwWjrRcPI5ZbTTuM/FQ9LNvH9DFv3fKf/FDddP35fBUSOUfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:38:45.332945Z"},"content_sha256":"f37a970d4604bb740fd86891cc8bf7a24e58603aa3c9201afc5cfe4a4ec2e2f5","schema_version":"1.0","event_id":"sha256:f37a970d4604bb740fd86891cc8bf7a24e58603aa3c9201afc5cfe4a4ec2e2f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5SOKHRM26VFML6YE4IINZSFFDD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ngoc Thang Vu, Xiang Yu","submitted_at":"2017-05-30T18:23:18Z","abstract_excerpt":"We present a transition-based dependency parser that uses a convolutional neural network to compose word representations from characters. The character composition model shows great improvement over the word-lookup model, especially for parsing agglutinative languages. These improvements are even better than using pre-trained word embeddings from extra data. On the SPMRL data sets, our system outperforms the previous best greedy parser (Ballesteros et al., 2015) by a margin of 3% on average."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10814","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":"2026-05-18T00:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZiHRCKFb0wbgl3YjReEWd6EGAUDZ1KgTFs5vLiW5dnHAIMyt+schSzWN5z2XTZRsN5ttV2aA2b+PMb3YlHLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:38:45.333286Z"},"content_sha256":"3f712150423de8731fcae8b6011c4fef45b51cedbf8992df95387d7010c60c27","schema_version":"1.0","event_id":"sha256:3f712150423de8731fcae8b6011c4fef45b51cedbf8992df95387d7010c60c27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SOKHRM26VFML6YE4IINZSFFDD/bundle.json","state_url":"https://pith.science/pith/5SOKHRM26VFML6YE4IINZSFFDD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SOKHRM26VFML6YE4IINZSFFDD/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":"2026-06-02T04:38:45Z","links":{"resolver":"https://pith.science/pith/5SOKHRM26VFML6YE4IINZSFFDD","bundle":"https://pith.science/pith/5SOKHRM26VFML6YE4IINZSFFDD/bundle.json","state":"https://pith.science/pith/5SOKHRM26VFML6YE4IINZSFFDD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SOKHRM26VFML6YE4IINZSFFDD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5SOKHRM26VFML6YE4IINZSFFDD","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":"b968276d52f94f838b31484584af679c8eee379077e50a4163f1f9833f2cc4ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-30T18:23:18Z","title_canon_sha256":"f468ddd809ca0ae6adf00f94029c9768d5e95b8f82fdf1600dae172ba0cb6808"},"schema_version":"1.0","source":{"id":"1705.10814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10814","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10814v1","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10814","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"5SOKHRM26VFM","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SOKHRM26VFML6YE","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SOKHRM2","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:3f712150423de8731fcae8b6011c4fef45b51cedbf8992df95387d7010c60c27","target":"graph","created_at":"2026-05-18T00:43:20Z","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 present a transition-based dependency parser that uses a convolutional neural network to compose word representations from characters. The character composition model shows great improvement over the word-lookup model, especially for parsing agglutinative languages. These improvements are even better than using pre-trained word embeddings from extra data. On the SPMRL data sets, our system outperforms the previous best greedy parser (Ballesteros et al., 2015) by a margin of 3% on average.","authors_text":"Ngoc Thang Vu, Xiang Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-30T18:23:18Z","title":"Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10814","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:f37a970d4604bb740fd86891cc8bf7a24e58603aa3c9201afc5cfe4a4ec2e2f5","target":"record","created_at":"2026-05-18T00:43:20Z","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":"b968276d52f94f838b31484584af679c8eee379077e50a4163f1f9833f2cc4ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-30T18:23:18Z","title_canon_sha256":"f468ddd809ca0ae6adf00f94029c9768d5e95b8f82fdf1600dae172ba0cb6808"},"schema_version":"1.0","source":{"id":"1705.10814","kind":"arxiv","version":1}},"canonical_sha256":"ec9ca3c59af54ac5fb04e210dcc8a518dae915fba0e085c9aa3d592a213d8204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec9ca3c59af54ac5fb04e210dcc8a518dae915fba0e085c9aa3d592a213d8204","first_computed_at":"2026-05-18T00:43:20.169217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:20.169217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dmQhm+/oc65D2wfDJUv4EwFFo10FHtL4WP6YmlxrDTv0+MF09YFNY/cQ5gz2Je7teoEhL4YbMdxtc3iE98NNDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:20.169921Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f37a970d4604bb740fd86891cc8bf7a24e58603aa3c9201afc5cfe4a4ec2e2f5","sha256:3f712150423de8731fcae8b6011c4fef45b51cedbf8992df95387d7010c60c27"],"state_sha256":"831ee29d8091c6150171508b71ae2374a51ad5a01b07d4a6ce294607e22198db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XIijJIh7zzysI7+hu2YkkkslOD08IzhKjEkYF6sftF1eBO5QfYI9Kxf61M6lYJ4pBJd9i2hsov+uYRL+YuiDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:38:45.335845Z","bundle_sha256":"c318b8222b228e0055d998af374c444a7961721594b0077308f975a4ca732213"}}