{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FPIW3Y2ODY7Z465GRPGGWDOW3Q","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":"e08543d4c93fe9b6b03e29aedd576bb7b0e54c448c26719dbb41af98a7aee42c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T00:17:57Z","title_canon_sha256":"9f0795d106736cfc7572d7297fd29625f7f4da61a6727ada04bf2f85b3e262fd"},"schema_version":"1.0","source":{"id":"2606.12767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12767","created_at":"2026-06-12T01:08:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12767v1","created_at":"2026-06-12T01:08:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12767","created_at":"2026-06-12T01:08:50Z"},{"alias_kind":"pith_short_12","alias_value":"FPIW3Y2ODY7Z","created_at":"2026-06-12T01:08:50Z"},{"alias_kind":"pith_short_16","alias_value":"FPIW3Y2ODY7Z465G","created_at":"2026-06-12T01:08:50Z"},{"alias_kind":"pith_short_8","alias_value":"FPIW3Y2O","created_at":"2026-06-12T01:08:50Z"}],"graph_snapshots":[{"event_id":"sha256:b786bafddaf51d3986ad7299ac162cb6a805382b3befd643804cd984ff1f7f1c","target":"graph","created_at":"2026-06-12T01:08:50Z","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/2606.12767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system is expected to use. We study how TMK-based question generation strategies affect dataset quality for procedural and multi-hop reasoning.\n  We compare three strategies: strict generation from Task-Method-Knowledge (TMK) models, transcript-first generation with post-hoc TMK filtering, and TMK-aware generation that combines transcripts with structured guidance. To evaluate generated items, we introduce a grounding vali","authors_text":"Ashok K. Goel, Rahul K. Dass, Sarah Elshabrawy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T00:17:57Z","title":"Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12767","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":"sha256:1c55a59a9b003ea706fa6adc88362f4c58f8de7ca51c8beb25eb2f4df587483f","target":"record","created_at":"2026-06-12T01:08:50Z","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":"e08543d4c93fe9b6b03e29aedd576bb7b0e54c448c26719dbb41af98a7aee42c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T00:17:57Z","title_canon_sha256":"9f0795d106736cfc7572d7297fd29625f7f4da61a6727ada04bf2f85b3e262fd"},"schema_version":"1.0","source":{"id":"2606.12767","kind":"arxiv","version":1}},"canonical_sha256":"2bd16de34e1e3f9e7ba68bcc6b0dd6dc1b4bb844be1d3f529b388b8796bad170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bd16de34e1e3f9e7ba68bcc6b0dd6dc1b4bb844be1d3f529b388b8796bad170","first_computed_at":"2026-06-12T01:08:50.088938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:50.088938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G207n1rvZH90GgUwKQKbEn2AodQ0WYjr3ejl9H/3IcjI5oWlZ5pT8LioqQhwUahcR5obDSjK3heKrt1r+pvnBA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:50.089830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c55a59a9b003ea706fa6adc88362f4c58f8de7ca51c8beb25eb2f4df587483f","sha256:b786bafddaf51d3986ad7299ac162cb6a805382b3befd643804cd984ff1f7f1c"],"state_sha256":"b726b4220418b645444547843b11f84ff12ea9fb57e50c422a75c4c727e7fc96"}