{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IKZK4GN5VIJMZG2FAVUFDVPES6","short_pith_number":"pith:IKZK4GN5","canonical_record":{"source":{"id":"1804.08117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-22T14:26:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0af11419edf3e19bf1ff6a3851820a19340a31830d9cb7fba738c42b9e7a1f4c","abstract_canon_sha256":"8659cbf04c06c5f80a768d3f181d86ef64b59a6fdbdfe5253ec910260f708a8e"},"schema_version":"1.0"},"canonical_sha256":"42b2ae19bdaa12cc9b45056851d5e49788f6adb20946c93b01b4f82a70bd15b5","source":{"kind":"arxiv","id":"1804.08117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08117","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08117v1","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08117","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"IKZK4GN5VIJM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IKZK4GN5VIJMZG2F","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IKZK4GN5","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IKZK4GN5VIJMZG2FAVUFDVPES6","target":"record","payload":{"canonical_record":{"source":{"id":"1804.08117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-22T14:26:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0af11419edf3e19bf1ff6a3851820a19340a31830d9cb7fba738c42b9e7a1f4c","abstract_canon_sha256":"8659cbf04c06c5f80a768d3f181d86ef64b59a6fdbdfe5253ec910260f708a8e"},"schema_version":"1.0"},"canonical_sha256":"42b2ae19bdaa12cc9b45056851d5e49788f6adb20946c93b01b4f82a70bd15b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:49.475099Z","signature_b64":"IbUPFflJdjTfkPZBOIBlAXu/CboYiuOnz9dL376GhPHN0CgWjRMSs5pWx1DX6KozMUfKzTSANnf7s7hG9LPEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42b2ae19bdaa12cc9b45056851d5e49788f6adb20946c93b01b4f82a70bd15b5","last_reissued_at":"2026-05-18T00:17:49.474050Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:49.474050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.08117","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":"2026-05-18T00:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4QeN0fGkGd14flhHLw4aeVOOAlDfBaN7/uUIt6qh3m9lPl6siuS1Fo/1dtouoSyW8Qc+GStoeKurCVuk6PQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:30:29.124733Z"},"content_sha256":"3660a414379cc38189a8d22850f70d1f1c296ea1d41302b084fd6875713623db","schema_version":"1.0","event_id":"sha256:3660a414379cc38189a8d22850f70d1f1c296ea1d41302b084fd6875713623db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IKZK4GN5VIJMZG2FAVUFDVPES6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Masatoshi Tsuchiya","submitted_at":"2018-04-22T14:26:28Z","abstract_excerpt":"The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE) task. The proposed method, which is inspired by a statistical hypothesis test, consists of two phases: the first phase is to introduce the predictability of textual entailment labels as a null hypothesis which is extremely unacceptable if a target corpus has no hidden bias, and the second phase is to test the null hypothesis using a Naive Bayes model. The exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08117","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":"2026-05-18T00:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mn66OoXOkTfZJD2eACU46wF2tSt2Dj4hT3qu/QC7DcDO0qnSCiQm9zL8fxFrT8m3PR2+D2z+Y5GfPjNQ3os5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:30:29.125216Z"},"content_sha256":"acbbe041ebe8e6a29b8611f8e014eb80d63340de38ca0e00ff67070a09204f9c","schema_version":"1.0","event_id":"sha256:acbbe041ebe8e6a29b8611f8e014eb80d63340de38ca0e00ff67070a09204f9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/bundle.json","state_url":"https://pith.science/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/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":"2026-08-16T20:30:29Z","links":{"resolver":"https://pith.science/pith/IKZK4GN5VIJMZG2FAVUFDVPES6","bundle":"https://pith.science/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/bundle.json","state":"https://pith.science/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKZK4GN5VIJMZG2FAVUFDVPES6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IKZK4GN5VIJMZG2FAVUFDVPES6","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":"8659cbf04c06c5f80a768d3f181d86ef64b59a6fdbdfe5253ec910260f708a8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-22T14:26:28Z","title_canon_sha256":"0af11419edf3e19bf1ff6a3851820a19340a31830d9cb7fba738c42b9e7a1f4c"},"schema_version":"1.0","source":{"id":"1804.08117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08117","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08117v1","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08117","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"IKZK4GN5VIJM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IKZK4GN5VIJMZG2F","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IKZK4GN5","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:acbbe041ebe8e6a29b8611f8e014eb80d63340de38ca0e00ff67070a09204f9c","target":"graph","created_at":"2026-05-18T00:17:49Z","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":"The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE) task. The proposed method, which is inspired by a statistical hypothesis test, consists of two phases: the first phase is to introduce the predictability of textual entailment labels as a null hypothesis which is extremely unacceptable if a target corpus has no hidden bias, and the second phase is to test the null hypothesis using a Naive Bayes model. The exp","authors_text":"Masatoshi Tsuchiya","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-22T14:26:28Z","title":"Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08117","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":"sha256:3660a414379cc38189a8d22850f70d1f1c296ea1d41302b084fd6875713623db","target":"record","created_at":"2026-05-18T00:17:49Z","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":"8659cbf04c06c5f80a768d3f181d86ef64b59a6fdbdfe5253ec910260f708a8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-22T14:26:28Z","title_canon_sha256":"0af11419edf3e19bf1ff6a3851820a19340a31830d9cb7fba738c42b9e7a1f4c"},"schema_version":"1.0","source":{"id":"1804.08117","kind":"arxiv","version":1}},"canonical_sha256":"42b2ae19bdaa12cc9b45056851d5e49788f6adb20946c93b01b4f82a70bd15b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42b2ae19bdaa12cc9b45056851d5e49788f6adb20946c93b01b4f82a70bd15b5","first_computed_at":"2026-05-18T00:17:49.474050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:49.474050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IbUPFflJdjTfkPZBOIBlAXu/CboYiuOnz9dL376GhPHN0CgWjRMSs5pWx1DX6KozMUfKzTSANnf7s7hG9LPEDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:49.475099Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3660a414379cc38189a8d22850f70d1f1c296ea1d41302b084fd6875713623db","sha256:acbbe041ebe8e6a29b8611f8e014eb80d63340de38ca0e00ff67070a09204f9c"],"state_sha256":"4f6a8a028a23980a65423402991aa33b06552dd84b0886329031a1cd58fd543a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OyLYXZdRv1RNyvNckY8+mqzZMLK5BMHfzwCVojM5hVAvkfImDbEpPcHWV3XrxHfIOvl8GaiNZWLs03SpV7LuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:30:29.130846Z","bundle_sha256":"d02d95448476f324ecf857a394c482b41ffb929ae7616880f4ac4f784907d5e0"}}