{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MEUQEZLXSG4T2NO3Q7T246AXHH","short_pith_number":"pith:MEUQEZLX","schema_version":"1.0","canonical_sha256":"612902657791b93d35db87e7ae781739dc0af127f5a8281f901b0b3e318043f7","source":{"kind":"arxiv","id":"1609.07561","version":1},"attestation_state":"computed","paper":{"title":"Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Lingpeng Kong, Miguel Ballesteros, Noah A. Smith","submitted_at":"2016-09-24T02:58:26Z","abstract_excerpt":"We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy LSTM transition-based parsers with different random initializations. We cast this approach as minimum Bayes risk decoding (under the Hamming cost) and argue that weaker consensus within the ensemble is a useful signal of difficulty or ambiguity. The second parser is a \"distillation\" of the ensemble into a single model. We train the distillation parser using a structured hinge loss objective with a novel cost that in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1609.07561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-24T02:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"21cbe2f11c8001b37b13612fda4a9191172e043f7d1d24af84182976db2598c5","abstract_canon_sha256":"bd2cc4ebceb36cfa393ee3cabae714565e7129046d3a58b4cfe4916b43b5fe1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:56.068915Z","signature_b64":"XrwRJuE3XWdcG+YtTkEHvqApRFd6n8yjaIWR4zyAvqrD7N0tpla3mpO9Jyp56bynSJuk7a+5gWaeQzeKbY1sCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"612902657791b93d35db87e7ae781739dc0af127f5a8281f901b0b3e318043f7","last_reissued_at":"2026-05-18T01:03:56.068074Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:56.068074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Lingpeng Kong, Miguel Ballesteros, Noah A. Smith","submitted_at":"2016-09-24T02:58:26Z","abstract_excerpt":"We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy LSTM transition-based parsers with different random initializations. We cast this approach as minimum Bayes risk decoding (under the Hamming cost) and argue that weaker consensus within the ensemble is a useful signal of difficulty or ambiguity. The second parser is a \"distillation\" of the ensemble into a single model. We train the distillation parser using a structured hinge loss objective with a novel cost that in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.07561","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1609.07561","created_at":"2026-05-18T01:03:56.068203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.07561v1","created_at":"2026-05-18T01:03:56.068203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.07561","created_at":"2026-05-18T01:03:56.068203+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEUQEZLXSG4T","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEUQEZLXSG4T2NO3","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEUQEZLX","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH","json":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH.json","graph_json":"https://pith.science/api/pith-number/MEUQEZLXSG4T2NO3Q7T246AXHH/graph.json","events_json":"https://pith.science/api/pith-number/MEUQEZLXSG4T2NO3Q7T246AXHH/events.json","paper":"https://pith.science/paper/MEUQEZLX"},"agent_actions":{"view_html":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH","download_json":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH.json","view_paper":"https://pith.science/paper/MEUQEZLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.07561&json=true","fetch_graph":"https://pith.science/api/pith-number/MEUQEZLXSG4T2NO3Q7T246AXHH/graph.json","fetch_events":"https://pith.science/api/pith-number/MEUQEZLXSG4T2NO3Q7T246AXHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH/action/storage_attestation","attest_author":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH/action/author_attestation","sign_citation":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH/action/citation_signature","submit_replication":"https://pith.science/pith/MEUQEZLXSG4T2NO3Q7T246AXHH/action/replication_record"}},"created_at":"2026-05-18T01:03:56.068203+00:00","updated_at":"2026-05-18T01:03:56.068203+00:00"}