{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NXNGP67BVJUAGJBNJB5DVEIFSE","short_pith_number":"pith:NXNGP67B","schema_version":"1.0","canonical_sha256":"6dda67fbe1aa6803242d487a3a91059121c683a0e90ab3795e0f2f9c39d969c3","source":{"kind":"arxiv","id":"2405.08468","version":1},"attestation_state":"computed","paper":{"title":"Challenges and Opportunities in Text Generation Explainability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenza Amara, Mennatallah El-Assady, Rita Sevastjanova","submitted_at":"2024-05-14T09:44:52Z","abstract_excerpt":"The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text generation stands out as a primary objective of autoregressive models. The NLP community has begun to take a keen interest in gaining a deeper understanding of text generation, leading to the development of model-agnostic explainable artificial intelligence (xAI) methods tailored to this task. The design and evaluation of explainability methods are non-trivial since they depend on many factors involved in the text g"},"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":"2405.08468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T09:44:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d411872d5b699bad9f1bf5d68820190648eb18d4199c2cea4c5ec46fc64d8809","abstract_canon_sha256":"905c14579bebe55cb0810d51d5f2cdebbf5798cc633bacbb788da90be05957e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:00.770975Z","signature_b64":"ycYZRJTsH7thGw05BttD+lPp0/J80eoLFP2LyFMRNoIM1iWnrwTbfNXUf5+XZhDufEIm8+SLxIOVg86WgdDbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dda67fbe1aa6803242d487a3a91059121c683a0e90ab3795e0f2f9c39d969c3","last_reissued_at":"2026-07-05T08:19:00.770502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:00.770502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges and Opportunities in Text Generation Explainability","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenza Amara, Mennatallah El-Assady, Rita Sevastjanova","submitted_at":"2024-05-14T09:44:52Z","abstract_excerpt":"The necessity for interpretability in natural language processing (NLP) has risen alongside the growing prominence of large language models. Among the myriad tasks within NLP, text generation stands out as a primary objective of autoregressive models. The NLP community has begun to take a keen interest in gaining a deeper understanding of text generation, leading to the development of model-agnostic explainable artificial intelligence (xAI) methods tailored to this task. The design and evaluation of explainability methods are non-trivial since they depend on many factors involved in the text g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08468","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/2405.08468/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":"2405.08468","created_at":"2026-07-05T08:19:00.770559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08468v1","created_at":"2026-07-05T08:19:00.770559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08468","created_at":"2026-07-05T08:19:00.770559+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXNGP67BVJUA","created_at":"2026-07-05T08:19:00.770559+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXNGP67BVJUAGJBN","created_at":"2026-07-05T08:19:00.770559+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXNGP67B","created_at":"2026-07-05T08:19:00.770559+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/NXNGP67BVJUAGJBNJB5DVEIFSE","json":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE.json","graph_json":"https://pith.science/api/pith-number/NXNGP67BVJUAGJBNJB5DVEIFSE/graph.json","events_json":"https://pith.science/api/pith-number/NXNGP67BVJUAGJBNJB5DVEIFSE/events.json","paper":"https://pith.science/paper/NXNGP67B"},"agent_actions":{"view_html":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE","download_json":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE.json","view_paper":"https://pith.science/paper/NXNGP67B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/NXNGP67BVJUAGJBNJB5DVEIFSE/graph.json","fetch_events":"https://pith.science/api/pith-number/NXNGP67BVJUAGJBNJB5DVEIFSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE/action/storage_attestation","attest_author":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE/action/author_attestation","sign_citation":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE/action/citation_signature","submit_replication":"https://pith.science/pith/NXNGP67BVJUAGJBNJB5DVEIFSE/action/replication_record"}},"created_at":"2026-07-05T08:19:00.770559+00:00","updated_at":"2026-07-05T08:19:00.770559+00:00"}