{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5E7F26BWEJGAKDDXIFRNLDIHQ","short_pith_number":"pith:H5E7F26B","schema_version":"1.0","canonical_sha256":"3f49f2ebc1b112602863ba0b16ac683c0d74d1efb991cfea433fee866c695657","source":{"kind":"arxiv","id":"2402.00978","version":1},"attestation_state":"computed","paper":{"title":"An Information-Theoretic Approach to Analyze NLP Classification Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Luran Wang, Mark Gales, Vatsal Raina","submitted_at":"2024-02-01T19:49:44Z","abstract_excerpt":"Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single element input or multiple element inputs to predict an output variable, where an element is a block of text. Each text element has two components: an associated semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MC"},"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":"2402.00978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T19:49:44Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"00a8d07c79efab854f2bd00f56903a983b4233269ef8cafbba14f6b1bb18aacf","abstract_canon_sha256":"6599eb11cd86475e566e5ed5ca6182065a44581fd5b7f16fca8412c7596463e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:28.777645Z","signature_b64":"RWOafR6AuWo1Z50ByN29fnnDUyTSY7hsjJJ+SWtSDePS6baGSPg4hyNVdPpqXCx0AJbT1oKU3dzmFsm+wnnwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f49f2ebc1b112602863ba0b16ac683c0d74d1efb991cfea433fee866c695657","last_reissued_at":"2026-07-05T07:40:28.777225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:28.777225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information-Theoretic Approach to Analyze NLP Classification Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Luran Wang, Mark Gales, Vatsal Raina","submitted_at":"2024-02-01T19:49:44Z","abstract_excerpt":"Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single element input or multiple element inputs to predict an output variable, where an element is a block of text. Each text element has two components: an associated semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00978","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/2402.00978/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":"2402.00978","created_at":"2026-07-05T07:40:28.777280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00978v1","created_at":"2026-07-05T07:40:28.777280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00978","created_at":"2026-07-05T07:40:28.777280+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5E7F26BWEJG","created_at":"2026-07-05T07:40:28.777280+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5E7F26BWEJGAKDD","created_at":"2026-07-05T07:40:28.777280+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5E7F26B","created_at":"2026-07-05T07:40:28.777280+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/H5E7F26BWEJGAKDDXIFRNLDIHQ","json":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ.json","graph_json":"https://pith.science/api/pith-number/H5E7F26BWEJGAKDDXIFRNLDIHQ/graph.json","events_json":"https://pith.science/api/pith-number/H5E7F26BWEJGAKDDXIFRNLDIHQ/events.json","paper":"https://pith.science/paper/H5E7F26B"},"agent_actions":{"view_html":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ","download_json":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ.json","view_paper":"https://pith.science/paper/H5E7F26B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00978&json=true","fetch_graph":"https://pith.science/api/pith-number/H5E7F26BWEJGAKDDXIFRNLDIHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/H5E7F26BWEJGAKDDXIFRNLDIHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ/action/storage_attestation","attest_author":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ/action/author_attestation","sign_citation":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ/action/citation_signature","submit_replication":"https://pith.science/pith/H5E7F26BWEJGAKDDXIFRNLDIHQ/action/replication_record"}},"created_at":"2026-07-05T07:40:28.777280+00:00","updated_at":"2026-07-05T07:40:28.777280+00:00"}