{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RRE3ZIGXRLJVX23DYIAI6PBLSA","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":"334417969989724b08f19de271658550d7e1af864d745050ee1a905948cf9b97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T04:40:25Z","title_canon_sha256":"fc3c4730871a074c241812e7d0fc6883a5562ca74768de0cdc58e0afe26d5f3f"},"schema_version":"1.0","source":{"id":"2606.03144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03144","created_at":"2026-06-03T01:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03144v1","created_at":"2026-06-03T01:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03144","created_at":"2026-06-03T01:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"RRE3ZIGXRLJV","created_at":"2026-06-03T01:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"RRE3ZIGXRLJVX23D","created_at":"2026-06-03T01:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"RRE3ZIGX","created_at":"2026-06-03T01:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:a59bd8c3ca3c840201ada36c6a547ba3c46824d1358c089f09d9d3e786c1037d","target":"graph","created_at":"2026-06-03T01:05:32Z","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/2606.03144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood. We introduce GTBench, a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, comprising 63 problems organized into three groups of increasing difficulty: undergraduate definitions and basic properties (Group 1), algorithm tracing and structural reasoning (Group 2), and graduate-level proof construction (Group 3). Problems are sourced from verified academic mat","authors_text":"Deepti Gupta, Ibrahem ALJabea, Noujoud Nader, Patrick Diehl","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T04:40:25Z","title":"GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03144","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":"sha256:67bc220c411bfde0e1edeeb7583c654b33b29315d00504972a5fcee3255c25c0","target":"record","created_at":"2026-06-03T01:05:32Z","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":"334417969989724b08f19de271658550d7e1af864d745050ee1a905948cf9b97","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T04:40:25Z","title_canon_sha256":"fc3c4730871a074c241812e7d0fc6883a5562ca74768de0cdc58e0afe26d5f3f"},"schema_version":"1.0","source":{"id":"2606.03144","kind":"arxiv","version":1}},"canonical_sha256":"8c49bca0d78ad35beb63c2008f3c2b90311346642fe64ba6f6d736a5ff487c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c49bca0d78ad35beb63c2008f3c2b90311346642fe64ba6f6d736a5ff487c34","first_computed_at":"2026-06-03T01:05:32.938043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:32.938043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1wAbAnePu3TQu97v2Eu4riKFRPb8EW3U1t7nwTz+pYbUo6MkoZ1RsjZwiOht8Uz7n69j6cSd6kjtlRykEmsPBQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:32.938487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67bc220c411bfde0e1edeeb7583c654b33b29315d00504972a5fcee3255c25c0","sha256:a59bd8c3ca3c840201ada36c6a547ba3c46824d1358c089f09d9d3e786c1037d"],"state_sha256":"3e2f83d23067009e3a719fa9e8271203ddc06f78d8a6b0b0476ea3764994d272"}