{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D7FPYCOB3QDRFS77ZEJHRSRUTR","short_pith_number":"pith:D7FPYCOB","canonical_record":{"source":{"id":"2504.02111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-02T20:18:50Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d2cd71f620a6ae1c81d7a1148b6900a7bb2066c4bb49446a1302195ad37ae01f","abstract_canon_sha256":"d30bb92d2884d121fb28e6caa3149887afa373e78b219972fee5da1b3dcd1289"},"schema_version":"1.0"},"canonical_sha256":"1fcafc09c1dc0712cbffc91278ca349c5691329c4e28581ea00eadc7d912b1f7","source":{"kind":"arxiv","id":"2504.02111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02111","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02111v1","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02111","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_12","alias_value":"D7FPYCOB3QDR","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_16","alias_value":"D7FPYCOB3QDRFS77","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_8","alias_value":"D7FPYCOB","created_at":"2026-07-05T10:43:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D7FPYCOB3QDRFS77ZEJHRSRUTR","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-02T20:18:50Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d2cd71f620a6ae1c81d7a1148b6900a7bb2066c4bb49446a1302195ad37ae01f","abstract_canon_sha256":"d30bb92d2884d121fb28e6caa3149887afa373e78b219972fee5da1b3dcd1289"},"schema_version":"1.0"},"canonical_sha256":"1fcafc09c1dc0712cbffc91278ca349c5691329c4e28581ea00eadc7d912b1f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:50.748779Z","signature_b64":"5Fz8I3nrjxXVm4lbimOCRFsgZavxuVc+PiITYXKgZTwy/C7cX7C6fHGGpHkWEMOjAmyQtn5hfcu123Jb3RmICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fcafc09c1dc0712cbffc91278ca349c5691329c4e28581ea00eadc7d912b1f7","last_reissued_at":"2026-07-05T10:43:50.748363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:50.748363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02111","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":"2026-07-05T10:43:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jGsycXcJJTNNicCzwuNYJyZkvawgH5lm3/3RcT3uvopgnCVzjXI00gcrOTXf/D165Suhi4jXEyB/zvf08mg5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:12:22.118453Z"},"content_sha256":"6f97db05256bd613859b0e8ea5db8210c79d180cd9599b57c552505cbdb799d3","schema_version":"1.0","event_id":"sha256:6f97db05256bd613859b0e8ea5db8210c79d180cd9599b57c552505cbdb799d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D7FPYCOB3QDRFS77ZEJHRSRUTR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring LLM Reasoning Through Controlled Prompt Variations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Giannis Chatziveroglou, Maura Kelleher, Richard Yun","submitted_at":"2025-04-02T20:18:50Z","abstract_excerpt":"This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how well state-of-the-art models maintain logical consistency and correctness when confronted with four categories of prompt perturbations: irrelevant context, pathological instructions, factually relevant but non-essential context, and a combination of the latter two. Our experiments, conducted on thirteen open-source and closed-source LLMs, reveal that introducin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02111","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/2504.02111/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":"2026-07-05T10:43:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fa6iES0tJ8AK3DJEaQ2QquXNIpU8plRr8L4PZ/eZ54wZVjgkvODhfEwR+zQdejaF2Z9YleVYoLPTPRSkT/yCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:12:22.119025Z"},"content_sha256":"561cdd73893ef5c41b1d73e8182aba7eb9d619ed69b1bd3596f724b36a87fdf9","schema_version":"1.0","event_id":"sha256:561cdd73893ef5c41b1d73e8182aba7eb9d619ed69b1bd3596f724b36a87fdf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/bundle.json","state_url":"https://pith.science/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/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":"2026-08-07T23:12:22Z","links":{"resolver":"https://pith.science/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR","bundle":"https://pith.science/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/bundle.json","state":"https://pith.science/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7FPYCOB3QDRFS77ZEJHRSRUTR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D7FPYCOB3QDRFS77ZEJHRSRUTR","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":"d30bb92d2884d121fb28e6caa3149887afa373e78b219972fee5da1b3dcd1289","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-02T20:18:50Z","title_canon_sha256":"d2cd71f620a6ae1c81d7a1148b6900a7bb2066c4bb49446a1302195ad37ae01f"},"schema_version":"1.0","source":{"id":"2504.02111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02111","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02111v1","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02111","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_12","alias_value":"D7FPYCOB3QDR","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_16","alias_value":"D7FPYCOB3QDRFS77","created_at":"2026-07-05T10:43:50Z"},{"alias_kind":"pith_short_8","alias_value":"D7FPYCOB","created_at":"2026-07-05T10:43:50Z"}],"graph_snapshots":[{"event_id":"sha256:561cdd73893ef5c41b1d73e8182aba7eb9d619ed69b1bd3596f724b36a87fdf9","target":"graph","created_at":"2026-07-05T10:43:50Z","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/2504.02111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how well state-of-the-art models maintain logical consistency and correctness when confronted with four categories of prompt perturbations: irrelevant context, pathological instructions, factually relevant but non-essential context, and a combination of the latter two. Our experiments, conducted on thirteen open-source and closed-source LLMs, reveal that introducin","authors_text":"Giannis Chatziveroglou, Maura Kelleher, Richard Yun","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-02T20:18:50Z","title":"Exploring LLM Reasoning Through Controlled Prompt Variations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02111","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":"sha256:6f97db05256bd613859b0e8ea5db8210c79d180cd9599b57c552505cbdb799d3","target":"record","created_at":"2026-07-05T10:43:50Z","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":"d30bb92d2884d121fb28e6caa3149887afa373e78b219972fee5da1b3dcd1289","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-02T20:18:50Z","title_canon_sha256":"d2cd71f620a6ae1c81d7a1148b6900a7bb2066c4bb49446a1302195ad37ae01f"},"schema_version":"1.0","source":{"id":"2504.02111","kind":"arxiv","version":1}},"canonical_sha256":"1fcafc09c1dc0712cbffc91278ca349c5691329c4e28581ea00eadc7d912b1f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fcafc09c1dc0712cbffc91278ca349c5691329c4e28581ea00eadc7d912b1f7","first_computed_at":"2026-07-05T10:43:50.748363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:50.748363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Fz8I3nrjxXVm4lbimOCRFsgZavxuVc+PiITYXKgZTwy/C7cX7C6fHGGpHkWEMOjAmyQtn5hfcu123Jb3RmICw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:50.748779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f97db05256bd613859b0e8ea5db8210c79d180cd9599b57c552505cbdb799d3","sha256:561cdd73893ef5c41b1d73e8182aba7eb9d619ed69b1bd3596f724b36a87fdf9"],"state_sha256":"35f88478b115f6a155cb897a88a1251dac3bae923d3ce262d659c42fb5ba6356"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"arf71AYvcPXhZnKJz3Pm6/m+bbcAiVwTLuc5OflM82q2IQqJ7GuSyWpxrb2uvMlOZ0sdsj4C1qyrWxXg64SLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:12:22.122969Z","bundle_sha256":"0a852606263e04efb029783e50049f41da69f5d4e3f2ab69cc2f831d27be92b7"}}