{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YANKGR7A4XT64ZDSR2RBVV6A63","short_pith_number":"pith:YANKGR7A","canonical_record":{"source":{"id":"2605.23925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-04-20T10:53:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5c3c814797d299d2699cbe46b26bb4f4a90015a0bdcf5f59cc634979c002d31d","abstract_canon_sha256":"6df2acdd4969dc001f32aa3378e0f6d1b982b9387341d5a743220714644acf2e"},"schema_version":"1.0"},"canonical_sha256":"c01aa347e0e5e7ee64728ea21ad7c0f6e394d77e9f504f0bd1c8a90b63c49c2c","source":{"kind":"arxiv","id":"2605.23925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23925","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23925v1","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23925","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"YANKGR7A4XT6","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"YANKGR7A4XT64ZDS","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"YANKGR7A","created_at":"2026-05-26T00:02:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YANKGR7A4XT64ZDSR2RBVV6A63","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-04-20T10:53:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5c3c814797d299d2699cbe46b26bb4f4a90015a0bdcf5f59cc634979c002d31d","abstract_canon_sha256":"6df2acdd4969dc001f32aa3378e0f6d1b982b9387341d5a743220714644acf2e"},"schema_version":"1.0"},"canonical_sha256":"c01aa347e0e5e7ee64728ea21ad7c0f6e394d77e9f504f0bd1c8a90b63c49c2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T00:02:22.218398Z","signature_b64":"RewP0aiDywWO0FVJShJ8YSXAtSWmDqx+IJ3GkHOwSA2LjTKU0nOAWpeAqCupOPhX2omL8EO8oDCtZzcW1q4hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01aa347e0e5e7ee64728ea21ad7c0f6e394d77e9f504f0bd1c8a90b63c49c2c","last_reissued_at":"2026-05-26T00:02:22.217287Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T00:02:22.217287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23925","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":"2026-05-26T00:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a8RlZio4lc+iYakv78oPVv4szVGRJNKL4Mc9Au9uKN/hACpIiol0KjpBbCxV4ZHUksvBs/StZZVg/nwk9DdXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:09:57.355406Z"},"content_sha256":"dfc33395b2079b81106d61b354927da58bf6b0bfe2029845117d1452f0964b86","schema_version":"1.0","event_id":"sha256:dfc33395b2079b81106d61b354927da58bf6b0bfe2029845117d1452f0964b86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YANKGR7A4XT64ZDSR2RBVV6A63","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Moiz Imran, Sahan Bulathwela","submitted_at":"2026-04-20T10:53:48Z","abstract_excerpt":"Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models under-detect misconceptions when students reach a correct answer via flawed reasoning. Analysing real student responses from the Eedi mathematics platform, we show that 71% of these failures concentrate in just two question types, both sharing a common structure where flawed reasoning happens to produce the correct numerical answer. Comparing a fine-tuned T5 with a fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23925","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/2605.23925/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":"2026-05-26T00:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVd5bOWOAPh5bQ8JlWgiLNKlXLoNgPXdPbt2UD4dtcdI/GRiiHwLSD4bb3jlNibnULseKlWMPUQ9D2eFWWzqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:09:57.355967Z"},"content_sha256":"909c6e047c92483dc4c5217e7f10c608c1dc42bd78c4d5f903d611c44e591198","schema_version":"1.0","event_id":"sha256:909c6e047c92483dc4c5217e7f10c608c1dc42bd78c4d5f903d611c44e591198"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YANKGR7A4XT64ZDSR2RBVV6A63/bundle.json","state_url":"https://pith.science/pith/YANKGR7A4XT64ZDSR2RBVV6A63/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YANKGR7A4XT64ZDSR2RBVV6A63/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":"2026-08-11T21:09:57Z","links":{"resolver":"https://pith.science/pith/YANKGR7A4XT64ZDSR2RBVV6A63","bundle":"https://pith.science/pith/YANKGR7A4XT64ZDSR2RBVV6A63/bundle.json","state":"https://pith.science/pith/YANKGR7A4XT64ZDSR2RBVV6A63/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YANKGR7A4XT64ZDSR2RBVV6A63/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YANKGR7A4XT64ZDSR2RBVV6A63","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":"6df2acdd4969dc001f32aa3378e0f6d1b982b9387341d5a743220714644acf2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-04-20T10:53:48Z","title_canon_sha256":"5c3c814797d299d2699cbe46b26bb4f4a90015a0bdcf5f59cc634979c002d31d"},"schema_version":"1.0","source":{"id":"2605.23925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23925","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23925v1","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23925","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"YANKGR7A4XT6","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"YANKGR7A4XT64ZDS","created_at":"2026-05-26T00:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"YANKGR7A","created_at":"2026-05-26T00:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:909c6e047c92483dc4c5217e7f10c608c1dc42bd78c4d5f903d611c44e591198","target":"graph","created_at":"2026-05-26T00:02:22Z","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/2605.23925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models under-detect misconceptions when students reach a correct answer via flawed reasoning. Analysing real student responses from the Eedi mathematics platform, we show that 71% of these failures concentrate in just two question types, both sharing a common structure where flawed reasoning happens to produce the correct numerical answer. Comparing a fine-tuned T5 with a fr","authors_text":"Moiz Imran, Sahan Bulathwela","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-04-20T10:53:48Z","title":"Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23925","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:dfc33395b2079b81106d61b354927da58bf6b0bfe2029845117d1452f0964b86","target":"record","created_at":"2026-05-26T00:02:22Z","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":"6df2acdd4969dc001f32aa3378e0f6d1b982b9387341d5a743220714644acf2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-04-20T10:53:48Z","title_canon_sha256":"5c3c814797d299d2699cbe46b26bb4f4a90015a0bdcf5f59cc634979c002d31d"},"schema_version":"1.0","source":{"id":"2605.23925","kind":"arxiv","version":1}},"canonical_sha256":"c01aa347e0e5e7ee64728ea21ad7c0f6e394d77e9f504f0bd1c8a90b63c49c2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c01aa347e0e5e7ee64728ea21ad7c0f6e394d77e9f504f0bd1c8a90b63c49c2c","first_computed_at":"2026-05-26T00:02:22.217287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T00:02:22.217287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RewP0aiDywWO0FVJShJ8YSXAtSWmDqx+IJ3GkHOwSA2LjTKU0nOAWpeAqCupOPhX2omL8EO8oDCtZzcW1q4hDw==","signature_status":"signed_v1","signed_at":"2026-05-26T00:02:22.218398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfc33395b2079b81106d61b354927da58bf6b0bfe2029845117d1452f0964b86","sha256:909c6e047c92483dc4c5217e7f10c608c1dc42bd78c4d5f903d611c44e591198"],"state_sha256":"6e5d0d944e68961e7f1afa919b809c8608612adc3e4c907fb732d7f27edb80b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBjXyoRR8d6xQ8kCaMXk8BcigxznKuXGMcoNEs/cCwKNkJLk8/d182OyJRQD9KfRle2QwAWaYFA9wL7EEtMACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:09:57.361373Z","bundle_sha256":"760cf77a97064d276f50716fbc241dc707e70933b7cf3e6c30b5e7bcd47ff2fe"}}