{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZYHYHWRHBWB3CKI4WL6FGM4LGF","short_pith_number":"pith:ZYHYHWRH","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"},"canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","source":{"kind":"arxiv","id":"1901.10496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10496","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10496v1","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10496","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZYHYHWRHBWB3","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZYHYHWRHBWB3CKI4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZYHYHWRH","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZYHYHWRHBWB3CKI4WL6FGM4LGF","target":"record","payload":{"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"},"canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","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"},"source_kind":"arxiv","source_id":"1901.10496","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FoWUlXJDc5VBbs8oNs2rQAp7ceZO4zusnjn63DOrZA+faKIP6J9euRtDzaqrbPnUYAQOn1SrQHgDcM615f7EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:51:55.302213Z"},"content_sha256":"8309685c1fbdeac84f070f87a6035852adf548848d23b76403137e3160d05316","schema_version":"1.0","event_id":"sha256:8309685c1fbdeac84f070f87a6035852adf548848d23b76403137e3160d05316"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZYHYHWRHBWB3CKI4WL6FGM4LGF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4tnKGu7d9NAeem2VeVA2xUG6KNvMrnqqd4CgtJ+X2luw6ih6Kh6O6klrNeOCVWF9PectwRSf07fIaSd1kp1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:51:55.302897Z"},"content_sha256":"dcbe98e0b8e5b574248a2c6acbaa8d88d132cec45111f35c787dc20e09f15106","schema_version":"1.0","event_id":"sha256:dcbe98e0b8e5b574248a2c6acbaa8d88d132cec45111f35c787dc20e09f15106"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/bundle.json","state_url":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T04:51:55Z","links":{"resolver":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF","bundle":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/bundle.json","state":"https://pith.science/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYHYHWRHBWB3CKI4WL6FGM4LGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZYHYHWRHBWB3CKI4WL6FGM4LGF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aa50c9b5a16e6f9e43eebf2e747c747e12c226d43bf7f11953b30c02879f167a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-29T19:00:21Z","title_canon_sha256":"8173851592bdfa2fe109c743cf4382378caac2fd5a292aae8745ad59cd3ee7c6"},"schema_version":"1.0","source":{"id":"1901.10496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10496","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10496v1","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10496","created_at":"2026-05-17T23:55:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZYHYHWRHBWB3","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZYHYHWRHBWB3CKI4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZYHYHWRH","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:dcbe98e0b8e5b574248a2c6acbaa8d88d132cec45111f35c787dc20e09f15106","target":"graph","created_at":"2026-05-17T23:55:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Krisztian Balog, Trond Linjordet","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-29T19:00:21Z","title":"Impact of Training Dataset Size on Neural Answer Selection Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10496","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8309685c1fbdeac84f070f87a6035852adf548848d23b76403137e3160d05316","target":"record","created_at":"2026-05-17T23:55:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aa50c9b5a16e6f9e43eebf2e747c747e12c226d43bf7f11953b30c02879f167a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-01-29T19:00:21Z","title_canon_sha256":"8173851592bdfa2fe109c743cf4382378caac2fd5a292aae8745ad59cd3ee7c6"},"schema_version":"1.0","source":{"id":"1901.10496","kind":"arxiv","version":1}},"canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce0f83da270d83b1291cb2fc53338b315b500fea78ef463e804fa9dfebd40ec6","first_computed_at":"2026-05-17T23:55:06.803915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:06.803915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QNKQ/5ZpW/PiXieFLNKN5GNI00pWDXVV7PDjQ+Zajp+L3G6qbqPw1AWFsOfVYoAsFrcyA9lWg+VKMc7V6BOAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:06.804474Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8309685c1fbdeac84f070f87a6035852adf548848d23b76403137e3160d05316","sha256:dcbe98e0b8e5b574248a2c6acbaa8d88d132cec45111f35c787dc20e09f15106"],"state_sha256":"301c81cde04f1072067d9168c105f03b8b3844302b10106f78b9f52a893d8f30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99qoQZ6GlYB141TRM1q7yCRJsSkUv5XqUqEhi0KrVT3ZUkp6i4bMn9lXzuP7WzocHIeBCpxOJ2cSNjvpH+llDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:51:55.306667Z","bundle_sha256":"00044e478e1abc1b3ddd096edd6bdb07acfe858f6ca9658a19a94103c671fac9"}}