{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FAJJCCRIZZHLD364M3CPX3RHZD","short_pith_number":"pith:FAJJCCRI","canonical_record":{"source":{"id":"2601.19924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T09:22:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c3847cfab4ea9627fcd570e0673fcc661a915ef3a464869b59c5cbfaed6149a7","abstract_canon_sha256":"9be0b4289a37c7b6d2030e8a8fde9772c80325d89a04fafa37c001f4001d4319"},"schema_version":"1.0"},"canonical_sha256":"2812910a28ce4eb1efdc66c4fbee27c8df62ac51c61e6bf6da3022335d775fff","source":{"kind":"arxiv","id":"2601.19924","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.19924","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2601.19924v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19924","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"FAJJCCRIZZHL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FAJJCCRIZZHLD364","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FAJJCCRI","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FAJJCCRIZZHLD364M3CPX3RHZD","target":"record","payload":{"canonical_record":{"source":{"id":"2601.19924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T09:22:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c3847cfab4ea9627fcd570e0673fcc661a915ef3a464869b59c5cbfaed6149a7","abstract_canon_sha256":"9be0b4289a37c7b6d2030e8a8fde9772c80325d89a04fafa37c001f4001d4319"},"schema_version":"1.0"},"canonical_sha256":"2812910a28ce4eb1efdc66c4fbee27c8df62ac51c61e6bf6da3022335d775fff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.587836Z","signature_b64":"GEcomY8Bk3+Khk0S92E4+5g+qmD1gPoGINEGIIfOEyZta+ViLjFFBLQC0z148Tj4q+5KJpfZsGniS6V4oXW7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2812910a28ce4eb1efdc66c4fbee27c8df62ac51c61e6bf6da3022335d775fff","last_reissued_at":"2026-05-17T23:39:16.587073Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.587073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.19924","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luMIsy7f6QUcJGA4ZWEFcDFT88dzAWWS64FHXKa0mBTa4wF8VJFTcfQFn10NdHqXC623UW3WqonTzvHB0uoHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:38:40.066840Z"},"content_sha256":"f4e7ffc92d7b0acf85acec1a57f9348c1118a66680212b014f267d6f482d899b","schema_version":"1.0","event_id":"sha256:f4e7ffc92d7b0acf85acec1a57f9348c1118a66680212b014f267d6f482d899b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FAJJCCRIZZHLD364M3CPX3RHZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng cheng, Dongdong Ge, Yinan Sun, Yitian Chen, Zi Ling","submitted_at":"2026-01-09T09:22:33Z","abstract_excerpt":"We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this end, we introduce OPT-ENGINE, an extensible benchmark framework with quantifiable and controllable complexity. OPT-ENGINE spans ten canonical Operations Research problems, systematically scaling from Linear Programming to Mixed-Integer Programming, providing a structured environment to probe the limits of automated problem formulation and solving. Utilizing OPT-Engine, we address three pivotal research questions. Firs"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For the current SOTA paradigm, Solver-integrated Reasoning (SIR), the automated formulation of constraints represents the primary bottleneck.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the ten canonical problems and the chosen complexity scaling metrics (variables, constraints, integrality) sufficiently represent the space of real-world optimization modeling tasks that LLMs would encounter.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9c3fc2f0ceb5095e2a819ba56d33047d581664a6678ab39e105e890684cb7833"},"source":{"id":"2601.19924","kind":"arxiv","version":2},"verdict":{"id":"a9bcce02-5f71-486b-a47b-54af35ebb9b0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T16:15:21.254376Z","strongest_claim":"For the current SOTA paradigm, Solver-integrated Reasoning (SIR), the automated formulation of constraints represents the primary bottleneck.","one_line_summary":"OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the ten canonical problems and the chosen complexity scaling metrics (variables, constraints, integrality) sufficiently represent the space of real-world optimization modeling tasks that LLMs would encounter.","pith_extraction_headline":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales."},"references":{"count":43,"sample":[{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","ref_index":2,"cited_arxiv_id":"2312.11805","is_internal_anchor":true},{"doi":"","year":2024,"title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","work_id":"80e3e977-f1bb-4c83-8d0c-1ab0a0c5c3f1","ref_index":3,"cited_arxiv_id":"2403.05530","is_internal_anchor":true},{"doi":"","year":2024,"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","ref_index":4,"cited_arxiv_id":"2412.19437","is_internal_anchor":true},{"doi":"","year":2025,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":5,"cited_arxiv_id":"2501.12948","is_internal_anchor":true}],"resolved_work":43,"snapshot_sha256":"2ce58239370396c817464bfce08651c77a096182468c96fcae0b0da971e819be","internal_anchors":12},"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":"a9bcce02-5f71-486b-a47b-54af35ebb9b0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x7h9ms9hHJzomvoHjOUklLz4cPcMiH4MPBNscQ4wSSBxcZHwdhb8bmKxSzrhSMnd/kiAK+gAGT+3VjfHy+6bAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:38:40.067417Z"},"content_sha256":"63217574ea389ca861790f75dd7593804ca73d14d840173c8f56bc14f8289a17","schema_version":"1.0","event_id":"sha256:63217574ea389ca861790f75dd7593804ca73d14d840173c8f56bc14f8289a17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAJJCCRIZZHLD364M3CPX3RHZD/bundle.json","state_url":"https://pith.science/pith/FAJJCCRIZZHLD364M3CPX3RHZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAJJCCRIZZHLD364M3CPX3RHZD/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":"2026-05-28T04:38:40Z","links":{"resolver":"https://pith.science/pith/FAJJCCRIZZHLD364M3CPX3RHZD","bundle":"https://pith.science/pith/FAJJCCRIZZHLD364M3CPX3RHZD/bundle.json","state":"https://pith.science/pith/FAJJCCRIZZHLD364M3CPX3RHZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAJJCCRIZZHLD364M3CPX3RHZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FAJJCCRIZZHLD364M3CPX3RHZD","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":"9be0b4289a37c7b6d2030e8a8fde9772c80325d89a04fafa37c001f4001d4319","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T09:22:33Z","title_canon_sha256":"c3847cfab4ea9627fcd570e0673fcc661a915ef3a464869b59c5cbfaed6149a7"},"schema_version":"1.0","source":{"id":"2601.19924","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.19924","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2601.19924v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19924","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"FAJJCCRIZZHL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FAJJCCRIZZHLD364","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FAJJCCRI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:63217574ea389ca861790f75dd7593804ca73d14d840173c8f56bc14f8289a17","target":"graph","created_at":"2026-05-17T23:39:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"For the current SOTA paradigm, Solver-integrated Reasoning (SIR), the automated formulation of constraints represents the primary bottleneck."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the ten canonical problems and the chosen complexity scaling metrics (variables, constraints, integrality) sufficiently represent the space of real-world optimization modeling tasks that LLMs would encounter."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales."}],"snapshot_sha256":"9c3fc2f0ceb5095e2a819ba56d33047d581664a6678ab39e105e890684cb7833"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this end, we introduce OPT-ENGINE, an extensible benchmark framework with quantifiable and controllable complexity. OPT-ENGINE spans ten canonical Operations Research problems, systematically scaling from Linear Programming to Mixed-Integer Programming, providing a structured environment to probe the limits of automated problem formulation and solving. Utilizing OPT-Engine, we address three pivotal research questions. Firs","authors_text":"Cheng cheng, Dongdong Ge, Yinan Sun, Yitian Chen, Zi Ling","cross_cats":["cs.AI","cs.LG"],"headline":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T09:22:33Z","title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling"},"references":{"count":43,"internal_anchors":12,"resolved_work":43,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"2312.11805","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023},{"cited_arxiv_id":"2403.05530","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","work_id":"80e3e977-f1bb-4c83-8d0c-1ab0a0c5c3f1","year":2024},{"cited_arxiv_id":"2412.19437","doi":"","is_internal_anchor":true,"ref_index":4,"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},{"cited_arxiv_id":"2501.12948","doi":"","is_internal_anchor":true,"ref_index":5,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025}],"snapshot_sha256":"2ce58239370396c817464bfce08651c77a096182468c96fcae0b0da971e819be"},"source":{"id":"2601.19924","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T16:15:21.254376Z","id":"a9bcce02-5f71-486b-a47b-54af35ebb9b0","model_set":{"reader":"grok-4.3"},"one_line_summary":"OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Solver-integrated LLMs for optimization modeling are limited primarily by errors in automated constraint formulation as problem complexity scales.","strongest_claim":"For the current SOTA paradigm, Solver-integrated Reasoning (SIR), the automated formulation of constraints represents the primary bottleneck.","weakest_assumption":"The assumption that the ten canonical problems and the chosen complexity scaling metrics (variables, constraints, integrality) sufficiently represent the space of real-world optimization modeling tasks that LLMs would encounter."}},"verdict_id":"a9bcce02-5f71-486b-a47b-54af35ebb9b0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f4e7ffc92d7b0acf85acec1a57f9348c1118a66680212b014f267d6f482d899b","target":"record","created_at":"2026-05-17T23:39:16Z","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":"9be0b4289a37c7b6d2030e8a8fde9772c80325d89a04fafa37c001f4001d4319","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T09:22:33Z","title_canon_sha256":"c3847cfab4ea9627fcd570e0673fcc661a915ef3a464869b59c5cbfaed6149a7"},"schema_version":"1.0","source":{"id":"2601.19924","kind":"arxiv","version":2}},"canonical_sha256":"2812910a28ce4eb1efdc66c4fbee27c8df62ac51c61e6bf6da3022335d775fff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2812910a28ce4eb1efdc66c4fbee27c8df62ac51c61e6bf6da3022335d775fff","first_computed_at":"2026-05-17T23:39:16.587073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.587073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEcomY8Bk3+Khk0S92E4+5g+qmD1gPoGINEGIIfOEyZta+ViLjFFBLQC0z148Tj4q+5KJpfZsGniS6V4oXW7BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.587836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.19924","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4e7ffc92d7b0acf85acec1a57f9348c1118a66680212b014f267d6f482d899b","sha256:63217574ea389ca861790f75dd7593804ca73d14d840173c8f56bc14f8289a17"],"state_sha256":"cddbc543d43b67d88aa1928fcd838740d8d75d04d6e0cb6899d4ca03cba841e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFr7/bznbEYH6EXgmOfR7yU8lUIdCUnIJzqxDI7C4DmSooa20Mg71UAjpCIWlEXZRQ0P13TRa+xrn3E6HoRwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:38:40.069939Z","bundle_sha256":"c30a77875457c18e357b787ed638ac5d09195cb183b63e5ea1f644598a90f059"}}