{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EROTMRYABIACHCTIHKWHKGCIFM","short_pith_number":"pith:EROTMRYA","schema_version":"1.0","canonical_sha256":"245d3647000a00238a683aac7518482b09af9847710756bf066cb64dea74aec9","source":{"kind":"arxiv","id":"1911.03561","version":4},"attestation_state":"computed","paper":{"title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Mohammadshahi, James Henderson","submitted_at":"2019-11-08T22:14:35Z","abstract_excerpt":"We propose the Graph2Graph Transformer architecture for conditioning on and predicting arbitrary graphs, and apply it to the challenging task of transition-based dependency parsing. After proposing two novel Transformer models of transition-based dependency parsing as strong baselines, we show that adding the proposed mechanisms for conditioning on and predicting graphs of Graph2Graph Transformer results in significant improvements, both with and without BERT pre-training. The novel baselines and their integration with Graph2Graph Transformer significantly outperform the state-of-the-art in tr"},"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":"1911.03561","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T22:14:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9294878f0c63512a37d1a0be784c256e4d64cb646ccb50100216e223e2e059e7","abstract_canon_sha256":"35f59a9bc98fb9ea4c3c54911b85cf46fa13228d8da3d1ad80d14b1543e2684d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:27.845828Z","signature_b64":"FAdXwsQCZDXK3VUq1wz7jOfsHKZlYB/n8C0bU0so1s0NnpvJuOkhkhcS7mW2M9gwGb9LF6Eva+Dvf+6NC476BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"245d3647000a00238a683aac7518482b09af9847710756bf066cb64dea74aec9","last_reissued_at":"2026-07-05T02:24:27.845448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:27.845448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Mohammadshahi, James Henderson","submitted_at":"2019-11-08T22:14:35Z","abstract_excerpt":"We propose the Graph2Graph Transformer architecture for conditioning on and predicting arbitrary graphs, and apply it to the challenging task of transition-based dependency parsing. After proposing two novel Transformer models of transition-based dependency parsing as strong baselines, we show that adding the proposed mechanisms for conditioning on and predicting graphs of Graph2Graph Transformer results in significant improvements, both with and without BERT pre-training. The novel baselines and their integration with Graph2Graph Transformer significantly outperform the state-of-the-art in tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03561","kind":"arxiv","version":4},"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/1911.03561/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.03561","created_at":"2026-07-05T02:24:27.845505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03561v4","created_at":"2026-07-05T02:24:27.845505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03561","created_at":"2026-07-05T02:24:27.845505+00:00"},{"alias_kind":"pith_short_12","alias_value":"EROTMRYABIAC","created_at":"2026-07-05T02:24:27.845505+00:00"},{"alias_kind":"pith_short_16","alias_value":"EROTMRYABIACHCTI","created_at":"2026-07-05T02:24:27.845505+00:00"},{"alias_kind":"pith_short_8","alias_value":"EROTMRYA","created_at":"2026-07-05T02:24:27.845505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14098","citing_title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM","json":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM.json","graph_json":"https://pith.science/api/pith-number/EROTMRYABIACHCTIHKWHKGCIFM/graph.json","events_json":"https://pith.science/api/pith-number/EROTMRYABIACHCTIHKWHKGCIFM/events.json","paper":"https://pith.science/paper/EROTMRYA"},"agent_actions":{"view_html":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM","download_json":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM.json","view_paper":"https://pith.science/paper/EROTMRYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03561&json=true","fetch_graph":"https://pith.science/api/pith-number/EROTMRYABIACHCTIHKWHKGCIFM/graph.json","fetch_events":"https://pith.science/api/pith-number/EROTMRYABIACHCTIHKWHKGCIFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM/action/storage_attestation","attest_author":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM/action/author_attestation","sign_citation":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM/action/citation_signature","submit_replication":"https://pith.science/pith/EROTMRYABIACHCTIHKWHKGCIFM/action/replication_record"}},"created_at":"2026-07-05T02:24:27.845505+00:00","updated_at":"2026-07-05T02:24:27.845505+00:00"}