{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RTWD5I54TEAA3CNCW53KTU4AWH","short_pith_number":"pith:RTWD5I54","schema_version":"1.0","canonical_sha256":"8cec3ea3bc99000d89a2b776a9d380b1f0a7bec9e03f9194d944107380f431b6","source":{"kind":"arxiv","id":"2306.13467","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Graph Information in Transformer-based AMR Parsing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abelardo Carlos Mart\\'inez Lorenzo, Pavlo Vasylenko, Pere-Llu\\'is Huguet Cabot, Roberto Navigli","submitted_at":"2023-06-23T12:12:08Z","abstract_excerpt":"Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version of the AMR graph from a sentence. In this paper, we present LeakDistill, a model and method that explores a modification to the Transformer architecture, using structural adapters to explicitly incorporate graph information into the learned representations and improve AMR parsing performance. Our expe"},"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":"2306.13467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-23T12:12:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f543606536c79119840d65ddee54023336aa0a5e8b8dfecf8d61d28b9c292be","abstract_canon_sha256":"e785c5b8053f04e9ff9eb839870761d5125542b14ee83e933098e4ea7e2b3878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:05.711757Z","signature_b64":"jyeJhX66cMNJS1OgaTmPwE+hqB2HLklIuCMUmEo0/txNNkiAfwm9GqAZzzXDuWQf/NPvAk6benSKBZDMef2mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cec3ea3bc99000d89a2b776a9d380b1f0a7bec9e03f9194d944107380f431b6","last_reissued_at":"2026-07-05T06:24:05.711296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:05.711296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Graph Information in Transformer-based AMR Parsing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abelardo Carlos Mart\\'inez Lorenzo, Pavlo Vasylenko, Pere-Llu\\'is Huguet Cabot, Roberto Navigli","submitted_at":"2023-06-23T12:12:08Z","abstract_excerpt":"Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version of the AMR graph from a sentence. In this paper, we present LeakDistill, a model and method that explores a modification to the Transformer architecture, using structural adapters to explicitly incorporate graph information into the learned representations and improve AMR parsing performance. Our expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13467","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/2306.13467/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":"2306.13467","created_at":"2026-07-05T06:24:05.711369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13467v1","created_at":"2026-07-05T06:24:05.711369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13467","created_at":"2026-07-05T06:24:05.711369+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTWD5I54TEAA","created_at":"2026-07-05T06:24:05.711369+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTWD5I54TEAA3CNC","created_at":"2026-07-05T06:24:05.711369+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTWD5I54","created_at":"2026-07-05T06:24:05.711369+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/RTWD5I54TEAA3CNCW53KTU4AWH","json":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH.json","graph_json":"https://pith.science/api/pith-number/RTWD5I54TEAA3CNCW53KTU4AWH/graph.json","events_json":"https://pith.science/api/pith-number/RTWD5I54TEAA3CNCW53KTU4AWH/events.json","paper":"https://pith.science/paper/RTWD5I54"},"agent_actions":{"view_html":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH","download_json":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH.json","view_paper":"https://pith.science/paper/RTWD5I54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13467&json=true","fetch_graph":"https://pith.science/api/pith-number/RTWD5I54TEAA3CNCW53KTU4AWH/graph.json","fetch_events":"https://pith.science/api/pith-number/RTWD5I54TEAA3CNCW53KTU4AWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH/action/storage_attestation","attest_author":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH/action/author_attestation","sign_citation":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH/action/citation_signature","submit_replication":"https://pith.science/pith/RTWD5I54TEAA3CNCW53KTU4AWH/action/replication_record"}},"created_at":"2026-07-05T06:24:05.711369+00:00","updated_at":"2026-07-05T06:24:05.711369+00:00"}