{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QHVE2YXKNRF6QXBTH5IEY3TARP","short_pith_number":"pith:QHVE2YXK","canonical_record":{"source":{"id":"1605.08889","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-28T13:19:15Z","cross_cats_sorted":[],"title_canon_sha256":"1ae120da602ba98b9cdc3891ece88cda24d104c019f4248d196b4d92248385ca","abstract_canon_sha256":"3357d6ea0a4f4d63034b9b3b26b684f94217414398585453541a69f397adfbe5"},"schema_version":"1.0"},"canonical_sha256":"81ea4d62ea6c4be85c333f504c6e608bec112520b10bcf57dc9cb9a338b84cd6","source":{"kind":"arxiv","id":"1605.08889","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08889","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08889v2","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08889","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"QHVE2YXKNRF6","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QHVE2YXKNRF6QXBT","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QHVE2YXK","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QHVE2YXKNRF6QXBTH5IEY3TARP","target":"record","payload":{"canonical_record":{"source":{"id":"1605.08889","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-28T13:19:15Z","cross_cats_sorted":[],"title_canon_sha256":"1ae120da602ba98b9cdc3891ece88cda24d104c019f4248d196b4d92248385ca","abstract_canon_sha256":"3357d6ea0a4f4d63034b9b3b26b684f94217414398585453541a69f397adfbe5"},"schema_version":"1.0"},"canonical_sha256":"81ea4d62ea6c4be85c333f504c6e608bec112520b10bcf57dc9cb9a338b84cd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:01.120730Z","signature_b64":"Zi4SN8247pe91BXS3ichPIB9tVRFXlt6J+ONE4jvGJLZDpU7wOUMM0kO+c1jUVkM8JeJRPkrnC5AMT+LZztCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81ea4d62ea6c4be85c333f504c6e608bec112520b10bcf57dc9cb9a338b84cd6","last_reissued_at":"2026-05-18T01:04:01.120102Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:01.120102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.08889","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M3lIbWETjnf/BzoTLqEfEWj0EBy8owM3w8SpjfaKVvWVQNXi9CTRAEYp1euOeEO8jQCCsdqz7EnYi6BRm951Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:31:47.065201Z"},"content_sha256":"de087e7b1fbd5357ccb36b13a084741bfa3454d3e760daaedb91b96dde6172b0","schema_version":"1.0","event_id":"sha256:de087e7b1fbd5357ccb36b13a084741bfa3454d3e760daaedb91b96dde6172b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QHVE2YXKNRF6QXBTH5IEY3TARP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building an Evaluation Scale using Item Response Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wu, Hong Yu, John P. Lalor","submitted_at":"2016-05-28T13:19:15Z","abstract_excerpt":"Evaluation of NLP methods requires testing against a previously vetted gold-standard test set and reporting standard metrics (accuracy/precision/recall/F1). The current assumption is that all items in a given test set are equal with regards to difficulty and discriminating power. We propose Item Response Theory (IRT) from psychometrics as an alternative means for gold-standard test-set generation and NLP system evaluation. IRT is able to describe characteristics of individual items - their difficulty and discriminating power - and can account for these characteristics in its estimation of huma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08889","kind":"arxiv","version":2},"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":"2026-05-18T01:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UbHBsHRqrF41iOL9aEc1ir8ZWEXqgGmBdRhSqE0+usbTeUyKdsSVbC5aXUjihAmcfv8mRRthREmr+LKIwUgmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:31:47.065935Z"},"content_sha256":"38a1f2c4f4a41203253031060380949d8dfb2687d8dbd254237112a4b3bb71ed","schema_version":"1.0","event_id":"sha256:38a1f2c4f4a41203253031060380949d8dfb2687d8dbd254237112a4b3bb71ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/bundle.json","state_url":"https://pith.science/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/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":"2026-05-25T21:31:47Z","links":{"resolver":"https://pith.science/pith/QHVE2YXKNRF6QXBTH5IEY3TARP","bundle":"https://pith.science/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/bundle.json","state":"https://pith.science/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHVE2YXKNRF6QXBTH5IEY3TARP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QHVE2YXKNRF6QXBTH5IEY3TARP","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":"3357d6ea0a4f4d63034b9b3b26b684f94217414398585453541a69f397adfbe5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-28T13:19:15Z","title_canon_sha256":"1ae120da602ba98b9cdc3891ece88cda24d104c019f4248d196b4d92248385ca"},"schema_version":"1.0","source":{"id":"1605.08889","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08889","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08889v2","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08889","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"QHVE2YXKNRF6","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QHVE2YXKNRF6QXBT","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QHVE2YXK","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:38a1f2c4f4a41203253031060380949d8dfb2687d8dbd254237112a4b3bb71ed","target":"graph","created_at":"2026-05-18T01:04:01Z","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":"Evaluation of NLP methods requires testing against a previously vetted gold-standard test set and reporting standard metrics (accuracy/precision/recall/F1). The current assumption is that all items in a given test set are equal with regards to difficulty and discriminating power. We propose Item Response Theory (IRT) from psychometrics as an alternative means for gold-standard test-set generation and NLP system evaluation. IRT is able to describe characteristics of individual items - their difficulty and discriminating power - and can account for these characteristics in its estimation of huma","authors_text":"Hao Wu, Hong Yu, John P. Lalor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-28T13:19:15Z","title":"Building an Evaluation Scale using Item Response Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08889","kind":"arxiv","version":2},"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:de087e7b1fbd5357ccb36b13a084741bfa3454d3e760daaedb91b96dde6172b0","target":"record","created_at":"2026-05-18T01:04:01Z","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":"3357d6ea0a4f4d63034b9b3b26b684f94217414398585453541a69f397adfbe5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-28T13:19:15Z","title_canon_sha256":"1ae120da602ba98b9cdc3891ece88cda24d104c019f4248d196b4d92248385ca"},"schema_version":"1.0","source":{"id":"1605.08889","kind":"arxiv","version":2}},"canonical_sha256":"81ea4d62ea6c4be85c333f504c6e608bec112520b10bcf57dc9cb9a338b84cd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81ea4d62ea6c4be85c333f504c6e608bec112520b10bcf57dc9cb9a338b84cd6","first_computed_at":"2026-05-18T01:04:01.120102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:01.120102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zi4SN8247pe91BXS3ichPIB9tVRFXlt6J+ONE4jvGJLZDpU7wOUMM0kO+c1jUVkM8JeJRPkrnC5AMT+LZztCBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:01.120730Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.08889","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de087e7b1fbd5357ccb36b13a084741bfa3454d3e760daaedb91b96dde6172b0","sha256:38a1f2c4f4a41203253031060380949d8dfb2687d8dbd254237112a4b3bb71ed"],"state_sha256":"8fc61dcb7094ea2a69a03b4e3ab933ff9b1b63628b22db43b4a3f3478fe31a78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qOQts/+Bp9XZ7WokOvLePvIxnH8ldvPrsxPgOpXWzQ4lMvD+LjHBztAOlm2zyiLpN2VYUCcF48GoMVwk8ZeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:31:47.069609Z","bundle_sha256":"faad921f02fd01c51f9202ba4dcfca4c0bd1d8f4560a281a8d2d9e0e786244ff"}}