{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6SQRSM6R2KOHYQAMKP5MAQXKYD","short_pith_number":"pith:6SQRSM6R","schema_version":"1.0","canonical_sha256":"f4a11933d1d29c7c400c53fac042eac0f9aea1dbbc009cc9d6b286a3e5313ed2","source":{"kind":"arxiv","id":"2205.01464","version":1},"attestation_state":"computed","paper":{"title":"Inducing and Using Alignments for Transition-based AMR Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Drozdov, Andrew McCallum, Jiawei Zhou, Radu Florian, Ramon Fernandez Astudillo, Tahira Naseem, Yoon Kim","submitted_at":"2022-05-03T12:58:36Z","abstract_excerpt":"Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on c"},"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":"2205.01464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-03T12:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"7c1c1b712edb2af30ca1ab12c76b38a13f05809aa463e775347a4881daa4f8f7","abstract_canon_sha256":"b8b6de10a1feec294455683f2dc378d5119532b2d678eae76d7ac1981e9626dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:04.990742Z","signature_b64":"TR0AxIa6/yjpXTt7N6GppfhRrzMD2L59+9SLDze0PdVqwo4YidyPcEMxY8HkS8R+BCR6hkVnfEnmJWy97bUlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a11933d1d29c7c400c53fac042eac0f9aea1dbbc009cc9d6b286a3e5313ed2","last_reissued_at":"2026-07-05T04:20:04.990343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:04.990343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inducing and Using Alignments for Transition-based AMR Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Drozdov, Andrew McCallum, Jiawei Zhou, Radu Florian, Ramon Fernandez Astudillo, Tahira Naseem, Yoon Kim","submitted_at":"2022-05-03T12:58:36Z","abstract_excerpt":"Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01464","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.01464/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":"2205.01464","created_at":"2026-07-05T04:20:04.990402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01464v1","created_at":"2026-07-05T04:20:04.990402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01464","created_at":"2026-07-05T04:20:04.990402+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SQRSM6R2KOH","created_at":"2026-07-05T04:20:04.990402+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SQRSM6R2KOHYQAM","created_at":"2026-07-05T04:20:04.990402+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SQRSM6R","created_at":"2026-07-05T04:20:04.990402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07171","citing_title":"EventRR: Event Referential Reasoning for Referring Video Object Segmentation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD","json":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD.json","graph_json":"https://pith.science/api/pith-number/6SQRSM6R2KOHYQAMKP5MAQXKYD/graph.json","events_json":"https://pith.science/api/pith-number/6SQRSM6R2KOHYQAMKP5MAQXKYD/events.json","paper":"https://pith.science/paper/6SQRSM6R"},"agent_actions":{"view_html":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD","download_json":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD.json","view_paper":"https://pith.science/paper/6SQRSM6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01464&json=true","fetch_graph":"https://pith.science/api/pith-number/6SQRSM6R2KOHYQAMKP5MAQXKYD/graph.json","fetch_events":"https://pith.science/api/pith-number/6SQRSM6R2KOHYQAMKP5MAQXKYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD/action/storage_attestation","attest_author":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD/action/author_attestation","sign_citation":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD/action/citation_signature","submit_replication":"https://pith.science/pith/6SQRSM6R2KOHYQAMKP5MAQXKYD/action/replication_record"}},"created_at":"2026-07-05T04:20:04.990402+00:00","updated_at":"2026-07-05T04:20:04.990402+00:00"}