{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:E73BZ6KES255VISJYSKYHBHHAU","short_pith_number":"pith:E73BZ6KE","canonical_record":{"source":{"id":"1504.00854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-04-03T14:46:29Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8e8893c77f02e8a37e41de6b345c6385bf3fbc64147ef8301f9230d5755b7f77","abstract_canon_sha256":"e7c293a0abc7da6bfc5c511a1c0967088dc111b35042e31426ebb1c9ded0f022"},"schema_version":"1.0"},"canonical_sha256":"27f61cf94496bbdaa249c4958384e70510364769bdb2c4f15675b36328e0e20c","source":{"kind":"arxiv","id":"1504.00854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.00854","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"arxiv_version","alias_value":"1504.00854v1","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00854","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"pith_short_12","alias_value":"E73BZ6KES255","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"E73BZ6KES255VISJ","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"E73BZ6KE","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:E73BZ6KES255VISJYSKYHBHHAU","target":"record","payload":{"canonical_record":{"source":{"id":"1504.00854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-04-03T14:46:29Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8e8893c77f02e8a37e41de6b345c6385bf3fbc64147ef8301f9230d5755b7f77","abstract_canon_sha256":"e7c293a0abc7da6bfc5c511a1c0967088dc111b35042e31426ebb1c9ded0f022"},"schema_version":"1.0"},"canonical_sha256":"27f61cf94496bbdaa249c4958384e70510364769bdb2c4f15675b36328e0e20c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:36.882059Z","signature_b64":"1V+f6ezIZHZh3ysHvQUESUvSs3Wm9j1wD6JK4S3QBBMCmuY6kgjihT38UGVR/sckJq/RoAKmkzCIV+Y3tKaeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27f61cf94496bbdaa249c4958384e70510364769bdb2c4f15675b36328e0e20c","last_reissued_at":"2026-05-18T02:19:36.881526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:36.881526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.00854","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":"2026-05-18T02:19:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mjs3WI2apMbfk1nzgneuxoBFMhTqMldoeCuGKD+jO5x6VPIMhzDBf5CLVx4/mJiZrAaaYFQb9VepxaiyQDliCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T23:31:45.156157Z"},"content_sha256":"95436fca33d087a0918eb6c75297f2e03dc5019e98dfae1b7501fb2cec2712a4","schema_version":"1.0","event_id":"sha256:95436fca33d087a0918eb6c75297f2e03dc5019e98dfae1b7501fb2cec2712a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:E73BZ6KES255VISJYSKYHBHHAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluation Evaluation a Monte Carlo study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.AI","authors_text":"David M. W. Powers","submitted_at":"2015-04-03T14:46:29Z","abstract_excerpt":"Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expectation due to chance, the simple conditional probabilities Recall, Precision and Accuracy are not meaningful as evaluation measures, either individually or in combinations such as F-factor. The existence of bias in NLP measures leads to the 'improvement' of systems by increasing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.00854","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":"2026-05-18T02:19:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bzranxzHAPxJOWpy7W2/54cZImBF3soX6H7cIgGd2x9JjN5BU68o1ONX2iChWFnyzmIEXT7gRFMH+PUeq3bWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T23:31:45.156509Z"},"content_sha256":"2f6468840c6cb882a9d5e0ecf4c3e7447d6c13a815f997172d42d8d928bade1b","schema_version":"1.0","event_id":"sha256:2f6468840c6cb882a9d5e0ecf4c3e7447d6c13a815f997172d42d8d928bade1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E73BZ6KES255VISJYSKYHBHHAU/bundle.json","state_url":"https://pith.science/pith/E73BZ6KES255VISJYSKYHBHHAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E73BZ6KES255VISJYSKYHBHHAU/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":"2026-06-26T23:31:45Z","links":{"resolver":"https://pith.science/pith/E73BZ6KES255VISJYSKYHBHHAU","bundle":"https://pith.science/pith/E73BZ6KES255VISJYSKYHBHHAU/bundle.json","state":"https://pith.science/pith/E73BZ6KES255VISJYSKYHBHHAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E73BZ6KES255VISJYSKYHBHHAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:E73BZ6KES255VISJYSKYHBHHAU","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":"e7c293a0abc7da6bfc5c511a1c0967088dc111b35042e31426ebb1c9ded0f022","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-04-03T14:46:29Z","title_canon_sha256":"8e8893c77f02e8a37e41de6b345c6385bf3fbc64147ef8301f9230d5755b7f77"},"schema_version":"1.0","source":{"id":"1504.00854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.00854","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"arxiv_version","alias_value":"1504.00854v1","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00854","created_at":"2026-05-18T02:19:36Z"},{"alias_kind":"pith_short_12","alias_value":"E73BZ6KES255","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"E73BZ6KES255VISJ","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"E73BZ6KE","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:2f6468840c6cb882a9d5e0ecf4c3e7447d6c13a815f997172d42d8d928bade1b","target":"graph","created_at":"2026-05-18T02:19:36Z","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":"Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expectation due to chance, the simple conditional probabilities Recall, Precision and Accuracy are not meaningful as evaluation measures, either individually or in combinations such as F-factor. The existence of bias in NLP measures leads to the 'improvement' of systems by increasing th","authors_text":"David M. W. Powers","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-04-03T14:46:29Z","title":"Evaluation Evaluation a Monte Carlo study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.00854","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":"sha256:95436fca33d087a0918eb6c75297f2e03dc5019e98dfae1b7501fb2cec2712a4","target":"record","created_at":"2026-05-18T02:19:36Z","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":"e7c293a0abc7da6bfc5c511a1c0967088dc111b35042e31426ebb1c9ded0f022","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-04-03T14:46:29Z","title_canon_sha256":"8e8893c77f02e8a37e41de6b345c6385bf3fbc64147ef8301f9230d5755b7f77"},"schema_version":"1.0","source":{"id":"1504.00854","kind":"arxiv","version":1}},"canonical_sha256":"27f61cf94496bbdaa249c4958384e70510364769bdb2c4f15675b36328e0e20c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27f61cf94496bbdaa249c4958384e70510364769bdb2c4f15675b36328e0e20c","first_computed_at":"2026-05-18T02:19:36.881526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:19:36.881526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1V+f6ezIZHZh3ysHvQUESUvSs3Wm9j1wD6JK4S3QBBMCmuY6kgjihT38UGVR/sckJq/RoAKmkzCIV+Y3tKaeDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:19:36.882059Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.00854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95436fca33d087a0918eb6c75297f2e03dc5019e98dfae1b7501fb2cec2712a4","sha256:2f6468840c6cb882a9d5e0ecf4c3e7447d6c13a815f997172d42d8d928bade1b"],"state_sha256":"9bee565b6b00af06ca81e29e603a35fda898690b37412af2a9d150459881a6cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W15wCdq7wTG6VIIXeKbbkqsy6ATZf/ZMr11pdfPtaFs/mu5xZmSnHPU/EPzUp7xDWuHkOhpcT5Xwo2H3j9GSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T23:31:45.158301Z","bundle_sha256":"b32f799f20caf694b3727e8523d85ede7180b6312a40300b27a4ae2ce4788854"}}