{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:L6C2F2BUA67F4K6FWBPAXFMAAH","short_pith_number":"pith:L6C2F2BU","canonical_record":{"source":{"id":"1806.03578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T03:50:10Z","cross_cats_sorted":[],"title_canon_sha256":"2bd01d197eb7ff5b3c48471223cc97b8582591b64a60a6a6936d66155149d464","abstract_canon_sha256":"0ad3b500819862a4c720dd8a7e11ca9a9717ab079d50514b24c8214178574e46"},"schema_version":"1.0"},"canonical_sha256":"5f85a2e83407be5e2bc5b05e0b958001e08dc5ec02403f9f840b03a1764d386f","source":{"kind":"arxiv","id":"1806.03578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03578","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03578v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03578","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"L6C2F2BUA67F","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L6C2F2BUA67F4K6F","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L6C2F2BU","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:L6C2F2BUA67F4K6FWBPAXFMAAH","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T03:50:10Z","cross_cats_sorted":[],"title_canon_sha256":"2bd01d197eb7ff5b3c48471223cc97b8582591b64a60a6a6936d66155149d464","abstract_canon_sha256":"0ad3b500819862a4c720dd8a7e11ca9a9717ab079d50514b24c8214178574e46"},"schema_version":"1.0"},"canonical_sha256":"5f85a2e83407be5e2bc5b05e0b958001e08dc5ec02403f9f840b03a1764d386f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:42.911345Z","signature_b64":"wbs9cSAOU3Y9e/hUlqbp4u6ejC/JuGM9TxXR+BeB2Yyb3Ja3euPVaavYKua61ZxltVFm34pjSa7VJsvf+cpuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f85a2e83407be5e2bc5b05e0b958001e08dc5ec02403f9f840b03a1764d386f","last_reissued_at":"2026-05-18T00:13:42.910452Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:42.910452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03578","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":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvQhmm/W960KYitjp7yYIfAjH2MjMdmUtgqbewRiivAHIhkRCIFjvRIw/0pnfrrglBTzEiyIfNrYj/ykZqLYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:45:54.311618Z"},"content_sha256":"c7283062379e726f1572e25f94244e4040e7707c64b9e1c7e03568dab7c7f046","schema_version":"1.0","event_id":"sha256:c7283062379e726f1572e25f94244e4040e7707c64b9e1c7e03568dab7c7f046"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:L6C2F2BUA67F4K6FWBPAXFMAAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"An Yang, Jing Liu, Kai Liu, Sujian Li, Yajuan Lyu","submitted_at":"2018-06-10T03:50:10Z","abstract_excerpt":"Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU. However, bias may appear when these metrics are used for specific question types, especially questions inquiring yes-no opinions and entity lists. In this paper, we make adaptations on the metrics to better correlate n-gram overlap with the human judgment for answers to these two question types. Statistical analysis proves the effectiveness of our approach. Our adaptations may provide posit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03578","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":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOTPeuVHadvwVWvumqVw3DbAudeKcy0u2o220YynrNozzNfu/BjwpH4DZPY+/XrgHqNF9eT+kbRvdsyzQE83Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:45:54.311949Z"},"content_sha256":"6cf37983d1bef19bd6581527f95e72d722050f5ffe003681f5a207ea4352c3f0","schema_version":"1.0","event_id":"sha256:6cf37983d1bef19bd6581527f95e72d722050f5ffe003681f5a207ea4352c3f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/bundle.json","state_url":"https://pith.science/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/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":"2026-07-02T09:45:54Z","links":{"resolver":"https://pith.science/pith/L6C2F2BUA67F4K6FWBPAXFMAAH","bundle":"https://pith.science/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/bundle.json","state":"https://pith.science/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6C2F2BUA67F4K6FWBPAXFMAAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:L6C2F2BUA67F4K6FWBPAXFMAAH","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":"0ad3b500819862a4c720dd8a7e11ca9a9717ab079d50514b24c8214178574e46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T03:50:10Z","title_canon_sha256":"2bd01d197eb7ff5b3c48471223cc97b8582591b64a60a6a6936d66155149d464"},"schema_version":"1.0","source":{"id":"1806.03578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03578","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03578v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03578","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"L6C2F2BUA67F","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L6C2F2BUA67F4K6F","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L6C2F2BU","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:6cf37983d1bef19bd6581527f95e72d722050f5ffe003681f5a207ea4352c3f0","target":"graph","created_at":"2026-05-18T00:13:42Z","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":"Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU. However, bias may appear when these metrics are used for specific question types, especially questions inquiring yes-no opinions and entity lists. In this paper, we make adaptations on the metrics to better correlate n-gram overlap with the human judgment for answers to these two question types. Statistical analysis proves the effectiveness of our approach. Our adaptations may provide posit","authors_text":"An Yang, Jing Liu, Kai Liu, Sujian Li, Yajuan Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T03:50:10Z","title":"Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03578","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:c7283062379e726f1572e25f94244e4040e7707c64b9e1c7e03568dab7c7f046","target":"record","created_at":"2026-05-18T00:13:42Z","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":"0ad3b500819862a4c720dd8a7e11ca9a9717ab079d50514b24c8214178574e46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T03:50:10Z","title_canon_sha256":"2bd01d197eb7ff5b3c48471223cc97b8582591b64a60a6a6936d66155149d464"},"schema_version":"1.0","source":{"id":"1806.03578","kind":"arxiv","version":1}},"canonical_sha256":"5f85a2e83407be5e2bc5b05e0b958001e08dc5ec02403f9f840b03a1764d386f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f85a2e83407be5e2bc5b05e0b958001e08dc5ec02403f9f840b03a1764d386f","first_computed_at":"2026-05-18T00:13:42.910452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:42.910452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbs9cSAOU3Y9e/hUlqbp4u6ejC/JuGM9TxXR+BeB2Yyb3Ja3euPVaavYKua61ZxltVFm34pjSa7VJsvf+cpuDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:42.911345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7283062379e726f1572e25f94244e4040e7707c64b9e1c7e03568dab7c7f046","sha256:6cf37983d1bef19bd6581527f95e72d722050f5ffe003681f5a207ea4352c3f0"],"state_sha256":"542c8a4841c8304277152fc5e3ea3b38be7105271943ad1cef2a2e48c836d98c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FU8Tt3YwnUPHGdrCahOGC/nTD52x2juQd0W2s7lWAfd6j6VkT+adR2bvPOa1UZ+1j9jTBpa3XD6PQo6nTIzsAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T09:45:54.313756Z","bundle_sha256":"aaaef36770ae8c057efaba4c0b7267c9c3b840f362ca62bf6a9401492f8647dd"}}