{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZYHYHWRHBWB3CKI4WL6FGM4LGF","short_pith_number":"pith:ZYHYHWRH","schema_version":"1.0","canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","source":{"kind":"arxiv","id":"1901.10496","version":1},"attestation_state":"computed","paper":{"title":"Impact of Training Dataset Size on Neural Answer Selection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Krisztian Balog, Trond Linjordet","submitted_at":"2019-01-29T19:00:21Z","abstract_excerpt":"It is held as a truism that deep neural networks require large datasets to train effective models. However, large datasets, especially with high-quality labels, can be expensive to obtain. This study sets out to investigate (i) how large a dataset must be to train well-performing models, and (ii) what impact can be shown from fractional changes to the dataset size. A practical method to investigate these questions is to train a collection of deep neural answer selection models using fractional subsets of varying sizes of an initial dataset. We observe that dataset size has a conspicuous lack o"},"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":"1901.10496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-29T19:00:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8173851592bdfa2fe109c743cf4382378caac2fd5a292aae8745ad59cd3ee7c6","abstract_canon_sha256":"aa50c9b5a16e6f9e43eebf2e747c747e12c226d43bf7f11953b30c02879f167a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:06.804474Z","signature_b64":"3QNKQ/5ZpW/PiXieFLNKN5GNI00pWDXVV7PDjQ+Zajp+L3G6qbqPw1AWFsOfVYoAsFrcyA9lWg+VKMc7V6BOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","last_reissued_at":"2026-05-17T23:55:06.803915Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:06.803915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Training Dataset Size on Neural Answer Selection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Krisztian Balog, Trond Linjordet","submitted_at":"2019-01-29T19:00:21Z","abstract_excerpt":"It is held as a truism that deep neural networks require large datasets to train effective models. However, large datasets, especially with high-quality labels, can be expensive to obtain. This study sets out to investigate (i) how large a dataset must be to train well-performing models, and (ii) what impact can be shown from fractional changes to the dataset size. A practical method to investigate these questions is to train a collection of deep neural answer selection models using fractional subsets of varying sizes of an initial dataset. We observe that dataset size has a conspicuous lack o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10496","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":""},"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":"1901.10496","created_at":"2026-05-17T23:55:06.804023+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10496v1","created_at":"2026-05-17T23:55:06.804023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10496","created_at":"2026-05-17T23:55:06.804023+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYHYHWRHBWB3","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYHYHWRHBWB3CKI4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYHYHWRH","created_at":"2026-05-18T12:33:33.725879+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/ZYHYHWRHBWB3CKI4WL6FGM4LGF","json":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF.json","graph_json":"https://pith.science/api/pith-number/ZYHYHWRHBWB3CKI4WL6FGM4LGF/graph.json","events_json":"https://pith.science/api/pith-number/ZYHYHWRHBWB3CKI4WL6FGM4LGF/events.json","paper":"https://pith.science/paper/ZYHYHWRH"},"agent_actions":{"view_html":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF","download_json":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF.json","view_paper":"https://pith.science/paper/ZYHYHWRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10496&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYHYHWRHBWB3CKI4WL6FGM4LGF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYHYHWRHBWB3CKI4WL6FGM4LGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/action/storage_attestation","attest_author":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/action/author_attestation","sign_citation":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/action/citation_signature","submit_replication":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/action/replication_record"}},"created_at":"2026-05-17T23:55:06.804023+00:00","updated_at":"2026-05-17T23:55:06.804023+00:00"}