{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EYMLV22XAKYGCFXZSWBAN5WGPY","short_pith_number":"pith:EYMLV22X","schema_version":"1.0","canonical_sha256":"2618baeb5702b06116f9958206f6c67e2ab51b05cd80fb594384e40aff3892fe","source":{"kind":"arxiv","id":"2109.03756","version":1},"attestation_state":"computed","paper":{"title":"Diagnostics-Guided Explanation Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christina Lioma, Isabelle Augenstein, Jakob Grue Simonsen, Pepa Atanasova","submitted_at":"2021-09-08T16:27:52Z","abstract_excerpt":"Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such annotations are not available, explanations are often selected as those portions of the input that maximise a downstream task's performance, which corresponds to optimising an explanation's Faithfulness to a given model. Faithfulness is one of several so-called diagnostic properties, which prior work has identified as useful for gauging the quality of an expl"},"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":"2109.03756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-08T16:27:52Z","cross_cats_sorted":[],"title_canon_sha256":"002232827cfb4c0759848b89a891353cc113f5a5ba010d979dc5be9a8d562d67","abstract_canon_sha256":"c275dd8fce1c197b7fa05cd58b91fe3b6896dc6a123dbc110e6adee357b3d59c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:42.816290Z","signature_b64":"tGqBxCyVB0v/NLNDT5QK+AVVHHru/k0GptYTtPD8/01N40XnIiN2F0/nfKl9DQsFeVVk0HAxwthrDGG1eAiNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2618baeb5702b06116f9958206f6c67e2ab51b05cd80fb594384e40aff3892fe","last_reissued_at":"2026-07-05T03:12:42.815850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:42.815850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnostics-Guided Explanation Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christina Lioma, Isabelle Augenstein, Jakob Grue Simonsen, Pepa Atanasova","submitted_at":"2021-09-08T16:27:52Z","abstract_excerpt":"Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such annotations are not available, explanations are often selected as those portions of the input that maximise a downstream task's performance, which corresponds to optimising an explanation's Faithfulness to a given model. Faithfulness is one of several so-called diagnostic properties, which prior work has identified as useful for gauging the quality of an expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03756","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/2109.03756/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":"2109.03756","created_at":"2026-07-05T03:12:42.815917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03756v1","created_at":"2026-07-05T03:12:42.815917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03756","created_at":"2026-07-05T03:12:42.815917+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYMLV22XAKYG","created_at":"2026-07-05T03:12:42.815917+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYMLV22XAKYGCFXZ","created_at":"2026-07-05T03:12:42.815917+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYMLV22X","created_at":"2026-07-05T03:12:42.815917+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/EYMLV22XAKYGCFXZSWBAN5WGPY","json":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY.json","graph_json":"https://pith.science/api/pith-number/EYMLV22XAKYGCFXZSWBAN5WGPY/graph.json","events_json":"https://pith.science/api/pith-number/EYMLV22XAKYGCFXZSWBAN5WGPY/events.json","paper":"https://pith.science/paper/EYMLV22X"},"agent_actions":{"view_html":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY","download_json":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY.json","view_paper":"https://pith.science/paper/EYMLV22X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03756&json=true","fetch_graph":"https://pith.science/api/pith-number/EYMLV22XAKYGCFXZSWBAN5WGPY/graph.json","fetch_events":"https://pith.science/api/pith-number/EYMLV22XAKYGCFXZSWBAN5WGPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY/action/storage_attestation","attest_author":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY/action/author_attestation","sign_citation":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY/action/citation_signature","submit_replication":"https://pith.science/pith/EYMLV22XAKYGCFXZSWBAN5WGPY/action/replication_record"}},"created_at":"2026-07-05T03:12:42.815917+00:00","updated_at":"2026-07-05T03:12:42.815917+00:00"}