{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J2ZGI2I7DGVP5K67PW5E6TWIZP","short_pith_number":"pith:J2ZGI2I7","canonical_record":{"source":{"id":"2304.02015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cc23cc2ccf485a8080603358ed8d08a1c81bbb24a5d918394c5a98323ada7e9","abstract_canon_sha256":"db31b758088e5e9a3fa0f96de54eebf93899ff6fa592c4cf06a6227c633cacfc"},"schema_version":"1.0"},"canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","source":{"kind":"arxiv","id":"2304.02015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02015","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02015v1","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02015","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"J2ZGI2I7DGVP","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"J2ZGI2I7DGVP5K67","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"J2ZGI2I7","created_at":"2026-07-05T05:58:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J2ZGI2I7DGVP5K67PW5E6TWIZP","target":"record","payload":{"canonical_record":{"source":{"id":"2304.02015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cc23cc2ccf485a8080603358ed8d08a1c81bbb24a5d918394c5a98323ada7e9","abstract_canon_sha256":"db31b758088e5e9a3fa0f96de54eebf93899ff6fa592c4cf06a6227c633cacfc"},"schema_version":"1.0"},"canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:21.152426Z","signature_b64":"QEwARQ67CmmjOiCxYktFPl2Lhxu2ONkMuo5BEpFKcEfLZeYs0LYO+clZ3vm/nDRe2bEICCWc5GlFRdxUlYByCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","last_reissued_at":"2026-07-05T05:58:21.151931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:21.151931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.02015","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":"2026-07-05T05:58:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dQMth2xdkPWk3KIkCkcZ8GX+hxVPK7Ut8I0Wv3DyDqqj8vaZLJUPASNN7GWYbGjxYlvaXtNhbRY0qCJdhlyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:30:36.544000Z"},"content_sha256":"32fe209017fb2a9b01cc80f972c74cddf05208364a80f17899a27a2c6bc44c9a","schema_version":"1.0","event_id":"sha256:32fe209017fb2a9b01cc80f972c74cddf05208364a80f17899a27a2c6bc44c9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J2ZGI2I7DGVP5K67PW5E6TWIZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How well do Large Language Models perform in Arithmetic tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Hongyi Yuan, Songfang Huang, Wei Wang, Zheng Yuan","submitted_at":"2023-03-16T09:28:15Z","abstract_excerpt":"Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic expressions correctly for each step. To the best of our knowledge, there is no work to focus on evaluating the arithmetic ability of large language models. In this work, we propose an arithmetic dataset MATH 401 to test the latest large language models including GPT-4, ChatGPT, InstrctGPT, Galactica, and LLaMA with various arithmetic expression"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02015","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/2304.02015/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":"2026-07-05T05:58:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQlBdntj75pNt7/z6ImsqGgzbKO38hrPbXlpJJDhSnhT04rzrx/TgaypVDiGCKR+lP2cQruA5TEcgCWdcAl5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:30:36.544538Z"},"content_sha256":"9dc6166c59b486a51b3b5a40720bc3a65bbdaa1be0136503dbad94e13e982670","schema_version":"1.0","event_id":"sha256:9dc6166c59b486a51b3b5a40720bc3a65bbdaa1be0136503dbad94e13e982670"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/bundle.json","state_url":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/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":"2026-08-04T21:30:36Z","links":{"resolver":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP","bundle":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/bundle.json","state":"https://pith.science/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2ZGI2I7DGVP5K67PW5E6TWIZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J2ZGI2I7DGVP5K67PW5E6TWIZP","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":"db31b758088e5e9a3fa0f96de54eebf93899ff6fa592c4cf06a6227c633cacfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","title_canon_sha256":"0cc23cc2ccf485a8080603358ed8d08a1c81bbb24a5d918394c5a98323ada7e9"},"schema_version":"1.0","source":{"id":"2304.02015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02015","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02015v1","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02015","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"J2ZGI2I7DGVP","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"J2ZGI2I7DGVP5K67","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"J2ZGI2I7","created_at":"2026-07-05T05:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:9dc6166c59b486a51b3b5a40720bc3a65bbdaa1be0136503dbad94e13e982670","target":"graph","created_at":"2026-07-05T05:58:21Z","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/2304.02015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic expressions correctly for each step. To the best of our knowledge, there is no work to focus on evaluating the arithmetic ability of large language models. In this work, we propose an arithmetic dataset MATH 401 to test the latest large language models including GPT-4, ChatGPT, InstrctGPT, Galactica, and LLaMA with various arithmetic expression","authors_text":"Chuanqi Tan, Hongyi Yuan, Songfang Huang, Wei Wang, Zheng Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","title":"How well do Large Language Models perform in Arithmetic tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02015","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":"sha256:32fe209017fb2a9b01cc80f972c74cddf05208364a80f17899a27a2c6bc44c9a","target":"record","created_at":"2026-07-05T05:58:21Z","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":"db31b758088e5e9a3fa0f96de54eebf93899ff6fa592c4cf06a6227c633cacfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T09:28:15Z","title_canon_sha256":"0cc23cc2ccf485a8080603358ed8d08a1c81bbb24a5d918394c5a98323ada7e9"},"schema_version":"1.0","source":{"id":"2304.02015","kind":"arxiv","version":1}},"canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb264691f19aafeabdf7dba4f4ec8cbe0379872c8867d9f10848de6de3c33c2","first_computed_at":"2026-07-05T05:58:21.151931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:21.151931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QEwARQ67CmmjOiCxYktFPl2Lhxu2ONkMuo5BEpFKcEfLZeYs0LYO+clZ3vm/nDRe2bEICCWc5GlFRdxUlYByCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:21.152426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32fe209017fb2a9b01cc80f972c74cddf05208364a80f17899a27a2c6bc44c9a","sha256:9dc6166c59b486a51b3b5a40720bc3a65bbdaa1be0136503dbad94e13e982670"],"state_sha256":"294144e73a143cab6aa7474ff1d3b098af3a00028b6e98b3661ad1580affce42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i87/SbpfwkPwef16YTxFabMOXMO2yn/1doOU9ktTWyZm4/a9u+Gd7kJDrY1aj9VDwSVYYciZ3LHAYc3bAcA7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:30:36.548470Z","bundle_sha256":"a7d00030d768b3ec713f9ada8f30953a0f9ba01e6a53b1157d4a86f487c0eef5"}}