{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NKPF3R7BWISH6KCVDL3TYT7J7P","short_pith_number":"pith:NKPF3R7B","canonical_record":{"source":{"id":"2502.07747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T18:14:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f200cb889be1340b786299409e7cbe1d55ae6f5f78aecbc08cc23d26a6b5ddf","abstract_canon_sha256":"f9867615938d1e627e5567bb7f8aeffc356d951fc824bcbd504dbc35dedf0e46"},"schema_version":"1.0"},"canonical_sha256":"6a9e5dc7e1b2247f28551af73c4fe9fbd895fb107532e71a2a1dd7dd510a6b12","source":{"kind":"arxiv","id":"2502.07747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07747","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07747v1","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07747","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"NKPF3R7BWISH","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"NKPF3R7BWISH6KCV","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"NKPF3R7B","created_at":"2026-07-05T10:12:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NKPF3R7BWISH6KCVDL3TYT7J7P","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T18:14:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f200cb889be1340b786299409e7cbe1d55ae6f5f78aecbc08cc23d26a6b5ddf","abstract_canon_sha256":"f9867615938d1e627e5567bb7f8aeffc356d951fc824bcbd504dbc35dedf0e46"},"schema_version":"1.0"},"canonical_sha256":"6a9e5dc7e1b2247f28551af73c4fe9fbd895fb107532e71a2a1dd7dd510a6b12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:53.295356Z","signature_b64":"48xh4SM0GWdCFVpHr6POxzj4uz1mp5NpKo0NSJZa2QhULu4vNYzg/g0FRYeqgkAc1rLMO0+LuzPUYgNHnIJ8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9e5dc7e1b2247f28551af73c4fe9fbd895fb107532e71a2a1dd7dd510a6b12","last_reissued_at":"2026-07-05T10:12:53.294858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:53.294858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07747","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":"2026-07-05T10:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVVHFkZ+piYC9qq6xpLMTHQWnIR/1WsTtQVmwMMHVJNRuqXCN3gpgr6eWpQOrWEm5ZCkIa2ylUKQ4BVkUQgQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:11:53.445114Z"},"content_sha256":"1246eac805e251e7dcfa9420bf48c112e349dffbe219bad5bf13d88b388e23cb","schema_version":"1.0","event_id":"sha256:1246eac805e251e7dcfa9420bf48c112e349dffbe219bad5bf13d88b388e23cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NKPF3R7BWISH6KCVDL3TYT7J7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WHODUNIT: Evaluation benchmark for culprit detection in mystery stories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kshitij Gupta","submitted_at":"2025-02-11T18:14:44Z","abstract_excerpt":"We present a novel data set, WhoDunIt, to assess the deductive reasoning capabilities of large language models (LLM) within narrative contexts. Constructed from open domain mystery novels and short stories, the dataset challenges LLMs to identify the perpetrator after reading and comprehending the story. To evaluate model robustness, we apply a range of character-level name augmentations, including original names, name swaps, and substitutions with well-known real and/or fictional entities from popular discourse. We further use various prompting styles to investigate the influence of prompting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07747","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/2502.07747/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":"2026-07-05T10:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AtDfmSnZUfE9EFDpSNKjNLDYAkiDIzZ1VlnnXi2eB6nrhZ5FSfFOzXlYlDONG0MVZ26OOYs9yalbGcyyCZsyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:11:53.445665Z"},"content_sha256":"e9ab606b1b8c7d5fefcc3e8d19e5f9f8abbd86c1d613d56d373ac9376a576bb8","schema_version":"1.0","event_id":"sha256:e9ab606b1b8c7d5fefcc3e8d19e5f9f8abbd86c1d613d56d373ac9376a576bb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/bundle.json","state_url":"https://pith.science/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/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":"2026-08-10T22:11:53Z","links":{"resolver":"https://pith.science/pith/NKPF3R7BWISH6KCVDL3TYT7J7P","bundle":"https://pith.science/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/bundle.json","state":"https://pith.science/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKPF3R7BWISH6KCVDL3TYT7J7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NKPF3R7BWISH6KCVDL3TYT7J7P","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":"f9867615938d1e627e5567bb7f8aeffc356d951fc824bcbd504dbc35dedf0e46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T18:14:44Z","title_canon_sha256":"3f200cb889be1340b786299409e7cbe1d55ae6f5f78aecbc08cc23d26a6b5ddf"},"schema_version":"1.0","source":{"id":"2502.07747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07747","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07747v1","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07747","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"NKPF3R7BWISH","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"NKPF3R7BWISH6KCV","created_at":"2026-07-05T10:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"NKPF3R7B","created_at":"2026-07-05T10:12:53Z"}],"graph_snapshots":[{"event_id":"sha256:e9ab606b1b8c7d5fefcc3e8d19e5f9f8abbd86c1d613d56d373ac9376a576bb8","target":"graph","created_at":"2026-07-05T10:12:53Z","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/2502.07747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel data set, WhoDunIt, to assess the deductive reasoning capabilities of large language models (LLM) within narrative contexts. Constructed from open domain mystery novels and short stories, the dataset challenges LLMs to identify the perpetrator after reading and comprehending the story. To evaluate model robustness, we apply a range of character-level name augmentations, including original names, name swaps, and substitutions with well-known real and/or fictional entities from popular discourse. We further use various prompting styles to investigate the influence of prompting","authors_text":"Kshitij Gupta","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T18:14:44Z","title":"WHODUNIT: Evaluation benchmark for culprit detection in mystery stories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07747","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":"sha256:1246eac805e251e7dcfa9420bf48c112e349dffbe219bad5bf13d88b388e23cb","target":"record","created_at":"2026-07-05T10:12:53Z","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":"f9867615938d1e627e5567bb7f8aeffc356d951fc824bcbd504dbc35dedf0e46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T18:14:44Z","title_canon_sha256":"3f200cb889be1340b786299409e7cbe1d55ae6f5f78aecbc08cc23d26a6b5ddf"},"schema_version":"1.0","source":{"id":"2502.07747","kind":"arxiv","version":1}},"canonical_sha256":"6a9e5dc7e1b2247f28551af73c4fe9fbd895fb107532e71a2a1dd7dd510a6b12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a9e5dc7e1b2247f28551af73c4fe9fbd895fb107532e71a2a1dd7dd510a6b12","first_computed_at":"2026-07-05T10:12:53.294858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:53.294858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48xh4SM0GWdCFVpHr6POxzj4uz1mp5NpKo0NSJZa2QhULu4vNYzg/g0FRYeqgkAc1rLMO0+LuzPUYgNHnIJ8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:53.295356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1246eac805e251e7dcfa9420bf48c112e349dffbe219bad5bf13d88b388e23cb","sha256:e9ab606b1b8c7d5fefcc3e8d19e5f9f8abbd86c1d613d56d373ac9376a576bb8"],"state_sha256":"fe97ddb4fd4b90f818aa3619e53e84416deeea3b885cabefa949cee63eb0dd54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OyOpciOQDC12w+942PA5/6oJtbsFwQLlnr7eGFisPYoV0+EYriLEtxme1Jghts187nQWExdr0ehvHX5i3ReaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:11:53.451038Z","bundle_sha256":"4a39ac5bfb898d676fa63805d9c95b643dae2441af138a8ee5137a63623f252c"}}