{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XCF4J7EJMT6GPLCUIQIM6ATH6B","short_pith_number":"pith:XCF4J7EJ","schema_version":"1.0","canonical_sha256":"b88bc4fc8964fc67ac544410cf0267f04c42cf33e423ba59bf4d74fa238c9195","source":{"kind":"arxiv","id":"2212.02726","version":2},"attestation_state":"computed","paper":{"title":"Dataset vs Reality: Understanding Model Performance from the Perspective of Information Need","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Mengying Yu","submitted_at":"2022-12-06T03:28:09Z","abstract_excerpt":"Deep learning technologies have brought us many models that outperform human beings on a few benchmarks. An interesting question is: can these models well solve real-world problems with similar settings (e.g., identical input/output) to the benchmark datasets? We argue that a model is trained to answer the same information need for which the training dataset is created. Although some datasets may share high structural similarities, e.g., question-answer pairs for the question answering (QA) task and image-caption pairs for the image captioning (IC) task, they may represent different research t"},"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":"2212.02726","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2022-12-06T03:28:09Z","cross_cats_sorted":[],"title_canon_sha256":"d1508691082436945512841e50c853b781304ef20ea61f4e7bde0bc592471b91","abstract_canon_sha256":"2f677f965e03ffd1b56784944c85440ecc0556b5553dbb4c572803af8f6516c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:41.142746Z","signature_b64":"+dr3/gBrTmMynJSE6mwztp736rm/nAk+UtynIPhVAW7G+vogU7VB8GazzMg/2X44sqF005JebQ3UEQiqGlrNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b88bc4fc8964fc67ac544410cf0267f04c42cf33e423ba59bf4d74fa238c9195","last_reissued_at":"2026-07-05T06:42:41.142307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:41.142307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset vs Reality: Understanding Model Performance from the Perspective of Information Need","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Mengying Yu","submitted_at":"2022-12-06T03:28:09Z","abstract_excerpt":"Deep learning technologies have brought us many models that outperform human beings on a few benchmarks. An interesting question is: can these models well solve real-world problems with similar settings (e.g., identical input/output) to the benchmark datasets? We argue that a model is trained to answer the same information need for which the training dataset is created. Although some datasets may share high structural similarities, e.g., question-answer pairs for the question answering (QA) task and image-caption pairs for the image captioning (IC) task, they may represent different research t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02726","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/2212.02726/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":"2212.02726","created_at":"2026-07-05T06:42:41.142370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02726v2","created_at":"2026-07-05T06:42:41.142370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02726","created_at":"2026-07-05T06:42:41.142370+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCF4J7EJMT6G","created_at":"2026-07-05T06:42:41.142370+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCF4J7EJMT6GPLCU","created_at":"2026-07-05T06:42:41.142370+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCF4J7EJ","created_at":"2026-07-05T06:42:41.142370+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/XCF4J7EJMT6GPLCUIQIM6ATH6B","json":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B.json","graph_json":"https://pith.science/api/pith-number/XCF4J7EJMT6GPLCUIQIM6ATH6B/graph.json","events_json":"https://pith.science/api/pith-number/XCF4J7EJMT6GPLCUIQIM6ATH6B/events.json","paper":"https://pith.science/paper/XCF4J7EJ"},"agent_actions":{"view_html":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B","download_json":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B.json","view_paper":"https://pith.science/paper/XCF4J7EJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02726&json=true","fetch_graph":"https://pith.science/api/pith-number/XCF4J7EJMT6GPLCUIQIM6ATH6B/graph.json","fetch_events":"https://pith.science/api/pith-number/XCF4J7EJMT6GPLCUIQIM6ATH6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B/action/storage_attestation","attest_author":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B/action/author_attestation","sign_citation":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B/action/citation_signature","submit_replication":"https://pith.science/pith/XCF4J7EJMT6GPLCUIQIM6ATH6B/action/replication_record"}},"created_at":"2026-07-05T06:42:41.142370+00:00","updated_at":"2026-07-05T06:42:41.142370+00:00"}