{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YEOB7NJ56ZPNBO5XTTMHSBOOXF","short_pith_number":"pith:YEOB7NJ5","canonical_record":{"source":{"id":"2508.00143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T20:05:26Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f16211d3d66106e06569d579dce6bd9640024c5dcdde86ecff421737f722355a","abstract_canon_sha256":"072153be55e044246d9fb44f5b49ce404d56e3ab1157d8118b702c3fc4303307"},"schema_version":"1.0"},"canonical_sha256":"c11c1fb53df65ed0bbb79cd87905ceb9541559d0540edaaa355255e9df9c139f","source":{"kind":"arxiv","id":"2508.00143","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00143","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00143v1","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00143","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"YEOB7NJ56ZPN","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"YEOB7NJ56ZPNBO5X","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"YEOB7NJ5","created_at":"2026-07-05T11:46:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YEOB7NJ56ZPNBO5XTTMHSBOOXF","target":"record","payload":{"canonical_record":{"source":{"id":"2508.00143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T20:05:26Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f16211d3d66106e06569d579dce6bd9640024c5dcdde86ecff421737f722355a","abstract_canon_sha256":"072153be55e044246d9fb44f5b49ce404d56e3ab1157d8118b702c3fc4303307"},"schema_version":"1.0"},"canonical_sha256":"c11c1fb53df65ed0bbb79cd87905ceb9541559d0540edaaa355255e9df9c139f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:49.778843Z","signature_b64":"w7SODU/cDVkVmQROJLMVn4bfbjZOCLoLzZkVDf7OEopnuszpG/KNldH+D14Li7AP7K6voi7sVtw677aWvT41AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c11c1fb53df65ed0bbb79cd87905ceb9541559d0540edaaa355255e9df9c139f","last_reissued_at":"2026-07-05T11:46:49.778400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:49.778400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.00143","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":"2026-07-05T11:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W+LsHUUdXZ1bw/GMgXwo42x0E43S8gL6trjZutqjg0c6SmfkEWMN7a9LEnZFngzw9LoK0mO8qRWi1wmkCsjvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:16:22.286255Z"},"content_sha256":"fabf02ac964141e59ca91b5a57b1bb6d79153ef38993c9d6cccf33f92473cfa9","schema_version":"1.0","event_id":"sha256:fabf02ac964141e59ca91b5a57b1bb6d79153ef38993c9d6cccf33f92473cfa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YEOB7NJ56ZPNBO5XTTMHSBOOXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Agreement: Rethinking Ground Truth in Educational AI Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Conrad Borchers, Danielle R. Thomas, Kenneth R. Koedinger","submitted_at":"2025-07-31T20:05:26Z","abstract_excerpt":"Humans can be notoriously imperfect evaluators. They are often biased, unreliable, and unfit to define \"ground truth.\" Yet, given the surging need to produce large amounts of training data in educational applications using AI, traditional inter-rater reliability (IRR) metrics like Cohen's kappa remain central to validating labeled data. IRR remains a cornerstone of many machine learning pipelines for educational data. Take, for example, the classification of tutors' moves in dialogues or labeling open responses in machine-graded assessments. This position paper argues that overreliance on huma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00143","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.00143/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZRy06373bi75R+rZGXJOmsjSP4dkfIvNv0Z6ZK9nkB/QtCwv47Av1rnKhIluNsHGEovRtRGAFQIRyF2d+YeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:16:22.287106Z"},"content_sha256":"5428a4ee32624c814cbce12ab94233b70caf4a7fabaa716a76e107ad11a1623b","schema_version":"1.0","event_id":"sha256:5428a4ee32624c814cbce12ab94233b70caf4a7fabaa716a76e107ad11a1623b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/bundle.json","state_url":"https://pith.science/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/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":"2026-08-11T03:16:22Z","links":{"resolver":"https://pith.science/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF","bundle":"https://pith.science/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/bundle.json","state":"https://pith.science/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEOB7NJ56ZPNBO5XTTMHSBOOXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YEOB7NJ56ZPNBO5XTTMHSBOOXF","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":"072153be55e044246d9fb44f5b49ce404d56e3ab1157d8118b702c3fc4303307","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T20:05:26Z","title_canon_sha256":"f16211d3d66106e06569d579dce6bd9640024c5dcdde86ecff421737f722355a"},"schema_version":"1.0","source":{"id":"2508.00143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00143","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00143v1","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00143","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"YEOB7NJ56ZPN","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"YEOB7NJ56ZPNBO5X","created_at":"2026-07-05T11:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"YEOB7NJ5","created_at":"2026-07-05T11:46:49Z"}],"graph_snapshots":[{"event_id":"sha256:5428a4ee32624c814cbce12ab94233b70caf4a7fabaa716a76e107ad11a1623b","target":"graph","created_at":"2026-07-05T11:46:49Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.00143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can be notoriously imperfect evaluators. They are often biased, unreliable, and unfit to define \"ground truth.\" Yet, given the surging need to produce large amounts of training data in educational applications using AI, traditional inter-rater reliability (IRR) metrics like Cohen's kappa remain central to validating labeled data. IRR remains a cornerstone of many machine learning pipelines for educational data. Take, for example, the classification of tutors' moves in dialogues or labeling open responses in machine-graded assessments. This position paper argues that overreliance on huma","authors_text":"Conrad Borchers, Danielle R. Thomas, Kenneth R. Koedinger","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T20:05:26Z","title":"Beyond Agreement: Rethinking Ground Truth in Educational AI Annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00143","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:fabf02ac964141e59ca91b5a57b1bb6d79153ef38993c9d6cccf33f92473cfa9","target":"record","created_at":"2026-07-05T11:46:49Z","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":"072153be55e044246d9fb44f5b49ce404d56e3ab1157d8118b702c3fc4303307","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T20:05:26Z","title_canon_sha256":"f16211d3d66106e06569d579dce6bd9640024c5dcdde86ecff421737f722355a"},"schema_version":"1.0","source":{"id":"2508.00143","kind":"arxiv","version":1}},"canonical_sha256":"c11c1fb53df65ed0bbb79cd87905ceb9541559d0540edaaa355255e9df9c139f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c11c1fb53df65ed0bbb79cd87905ceb9541559d0540edaaa355255e9df9c139f","first_computed_at":"2026-07-05T11:46:49.778400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:49.778400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w7SODU/cDVkVmQROJLMVn4bfbjZOCLoLzZkVDf7OEopnuszpG/KNldH+D14Li7AP7K6voi7sVtw677aWvT41AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:49.778843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fabf02ac964141e59ca91b5a57b1bb6d79153ef38993c9d6cccf33f92473cfa9","sha256:5428a4ee32624c814cbce12ab94233b70caf4a7fabaa716a76e107ad11a1623b"],"state_sha256":"a6ac74b41756bc36311f674670319a9b7a90a2cdc77b5a124ae8c65e1509941b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/ynI00XUDf3xxZLYFAE6qoNOjwv50KTwQ2QTPYHtn4rLVgc4t+8oSqHuoFDooKG9phGrQvgdEsH6uU8Z4JeAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:16:22.306874Z","bundle_sha256":"c9efcb1b39586520e08346e11804189476d80d2f3a4ae87b2cda752c1d0e6eb8"}}