{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V4V567XQNGTPLAEVGHPR5PCP4G","short_pith_number":"pith:V4V567XQ","schema_version":"1.0","canonical_sha256":"af2bdf7ef069a6f5809531df1ebc4fe1ac11aecb3e9768f4f748c03a39d301b3","source":{"kind":"arxiv","id":"2112.07790","version":2},"attestation_state":"computed","paper":{"title":"Maximum Bayes Smatch Ensemble Distillation for AMR Parsing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Radu Florian, Ramon Fernandez Astudillo, Salim Roukos, Tahira Naseem, Thanh Lam Hoang, Young-Suk Lee","submitted_at":"2021-12-14T23:29:37Z","abstract_excerpt":"AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning. Self-learning techniques have also played a role in pushing performance forward. However, for most recent high performant parsers, the effect of self-learning and silver data augmentation seems to be fading. In this paper we propose to overcome this diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation. In an extensive experimental setup, we push single model "},"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":"2112.07790","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T23:29:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a37ef7f79f518d920752662f9ad0dedfe9dce787e4b6dff841c3ab131f371cf1","abstract_canon_sha256":"ffc1088d679436ffd42d48a0fbb6a68730cb6115381c1cfe9dd396c86290d145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:54.208766Z","signature_b64":"fdr2KgqDY3R/3ffWWajrXnVjYiaYXOnZxU7g7OAYB4E3mUoM1NmahFGcMsffsVoihpZ3hdN9wLehDX4zAAhBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2bdf7ef069a6f5809531df1ebc4fe1ac11aecb3e9768f4f748c03a39d301b3","last_reissued_at":"2026-07-05T04:20:54.208279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:54.208279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Bayes Smatch Ensemble Distillation for AMR Parsing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Radu Florian, Ramon Fernandez Astudillo, Salim Roukos, Tahira Naseem, Thanh Lam Hoang, Young-Suk Lee","submitted_at":"2021-12-14T23:29:37Z","abstract_excerpt":"AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning. Self-learning techniques have also played a role in pushing performance forward. However, for most recent high performant parsers, the effect of self-learning and silver data augmentation seems to be fading. In this paper we propose to overcome this diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation. In an extensive experimental setup, we push single model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07790","kind":"arxiv","version":2},"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/2112.07790/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":"2112.07790","created_at":"2026-07-05T04:20:54.208342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07790v2","created_at":"2026-07-05T04:20:54.208342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07790","created_at":"2026-07-05T04:20:54.208342+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4V567XQNGTP","created_at":"2026-07-05T04:20:54.208342+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4V567XQNGTPLAEV","created_at":"2026-07-05T04:20:54.208342+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4V567XQ","created_at":"2026-07-05T04:20:54.208342+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/V4V567XQNGTPLAEVGHPR5PCP4G","json":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G.json","graph_json":"https://pith.science/api/pith-number/V4V567XQNGTPLAEVGHPR5PCP4G/graph.json","events_json":"https://pith.science/api/pith-number/V4V567XQNGTPLAEVGHPR5PCP4G/events.json","paper":"https://pith.science/paper/V4V567XQ"},"agent_actions":{"view_html":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G","download_json":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G.json","view_paper":"https://pith.science/paper/V4V567XQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07790&json=true","fetch_graph":"https://pith.science/api/pith-number/V4V567XQNGTPLAEVGHPR5PCP4G/graph.json","fetch_events":"https://pith.science/api/pith-number/V4V567XQNGTPLAEVGHPR5PCP4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G/action/storage_attestation","attest_author":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G/action/author_attestation","sign_citation":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G/action/citation_signature","submit_replication":"https://pith.science/pith/V4V567XQNGTPLAEVGHPR5PCP4G/action/replication_record"}},"created_at":"2026-07-05T04:20:54.208342+00:00","updated_at":"2026-07-05T04:20:54.208342+00:00"}