{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LYBJAIC2ZGXFR7XUUQTJIDUDC3","short_pith_number":"pith:LYBJAIC2","canonical_record":{"source":{"id":"2602.07342","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-07T03:49:25Z","cross_cats_sorted":[],"title_canon_sha256":"48aa46042a6438d3916f11b3dbfb88c2a0f3820fab4d91a479b86bc9968306e7","abstract_canon_sha256":"09ff1b7536411fbd75f17ff9bc5c672c9dfa972c99eb2bf34a0cdced8bd6547f"},"schema_version":"1.0"},"canonical_sha256":"5e0290205ac9ae58fef4a426940e8316cf97059127a3d16179cc94be8ac488b5","source":{"kind":"arxiv","id":"2602.07342","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07342","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07342v2","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07342","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"LYBJAIC2ZGXF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LYBJAIC2ZGXFR7XU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LYBJAIC2","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LYBJAIC2ZGXFR7XUUQTJIDUDC3","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07342","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-07T03:49:25Z","cross_cats_sorted":[],"title_canon_sha256":"48aa46042a6438d3916f11b3dbfb88c2a0f3820fab4d91a479b86bc9968306e7","abstract_canon_sha256":"09ff1b7536411fbd75f17ff9bc5c672c9dfa972c99eb2bf34a0cdced8bd6547f"},"schema_version":"1.0"},"canonical_sha256":"5e0290205ac9ae58fef4a426940e8316cf97059127a3d16179cc94be8ac488b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.322930Z","signature_b64":"KYyjXwI7F4PPYo8eQcMY/5wFH/LYCOqcClVJ0/feZqgvFdmmAmFjSLgy9XjzvCuhmW6LJamEY8+27mh6WG+QDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e0290205ac9ae58fef4a426940e8316cf97059127a3d16179cc94be8ac488b5","last_reissued_at":"2026-05-18T02:44:31.322406Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.322406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07342","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":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBsfUFPXp7J6tmOzUrU3qxPTen8eNmtZhQu0vsyg7S40XmEHVVKg9GH5Ya3vVgVfRR5C5Mu4X8B12M/xs++3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:49:42.023532Z"},"content_sha256":"48defddee6b3b14f3f519b1712f81e6185e7828c28e85d8aac0d1cefa3669b7f","schema_version":"1.0","event_id":"sha256:48defddee6b3b14f3f519b1712f81e6185e7828c28e85d8aac0d1cefa3669b7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LYBJAIC2ZGXFR7XUUQTJIDUDC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lang Cao, Shengyue Guan, Yihao Liu","submitted_at":"2026-02-07T03:49:25Z","abstract_excerpt":"Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOP"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1b44a6b88d31c59a5dfb144f0bff82c76a3e6e5440c0138f5524f9f6b3f8c49"},"source":{"id":"2602.07342","kind":"arxiv","version":2},"verdict":{"id":"ca4685e4-28ca-4376-a74f-9019257a588c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:46:48.786277Z","strongest_claim":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance.","one_line_summary":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested.","pith_extraction_headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance."},"references":{"count":21,"sample":[{"doi":"","year":2024,"title":"Smart routing for sustainable supply chain net- works: An ai and knowledge graph driven approach. Applied Sciences, 15(14):8001. Elizabeth Fons, Rachneet Kaur, Soham Palande, Zhen Zeng, Tucker Balch, ","work_id":"9bb80603-0f99-4cf7-a321-48890f9836db","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","work_id":"4aff48d9-c46d-41d9-904b-52251e559596","ref_index":2,"cited_arxiv_id":"2503.21460","is_internal_anchor":true},{"doi":"","year":null,"title":"Identifier Extraction:The system first parses the user’s query to extract the primary trade_order_id","work_id":"387b9cb7-30c9-4c4d-bf40-efa410e3b2ce","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"An order may be split into multiple fulfillments","work_id":"f50b75f3-3350-4797-940f-f7a269c37a8d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Status Check:For each fulfillment_id iden- tified in the previous step, the system queries its real-time status","work_id":"5b2d833a-6d72-41fa-823c-caa82a1f9dcb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"f91a2040f821c20cba4d2e477d167512e1f1f3a0db466929ade5c0742b69753b","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1e466faa7fe7dcf62506c25e1f9c907ee62368e8f0650c45986e6920b5b7af44"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ca4685e4-28ca-4376-a74f-9019257a588c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjnug8cSyHHQWOF9IsbNeqYeYQ8ZJr1QcO1pIYTerNKjZezA9yFh6mpY5CaOLaxcyodFYVnT8IqsUhKH75N6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:49:42.024797Z"},"content_sha256":"a91498a31f128f582cba399261f7e6ba2876ac87f93446eef8c944d2f5b7729a","schema_version":"1.0","event_id":"sha256:a91498a31f128f582cba399261f7e6ba2876ac87f93446eef8c944d2f5b7729a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/bundle.json","state_url":"https://pith.science/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/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":"2026-06-01T12:49:42Z","links":{"resolver":"https://pith.science/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3","bundle":"https://pith.science/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/bundle.json","state":"https://pith.science/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYBJAIC2ZGXFR7XUUQTJIDUDC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYBJAIC2ZGXFR7XUUQTJIDUDC3","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":"09ff1b7536411fbd75f17ff9bc5c672c9dfa972c99eb2bf34a0cdced8bd6547f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-07T03:49:25Z","title_canon_sha256":"48aa46042a6438d3916f11b3dbfb88c2a0f3820fab4d91a479b86bc9968306e7"},"schema_version":"1.0","source":{"id":"2602.07342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07342","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07342v2","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07342","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"LYBJAIC2ZGXF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LYBJAIC2ZGXFR7XU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LYBJAIC2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:a91498a31f128f582cba399261f7e6ba2876ac87f93446eef8c944d2f5b7729a","target":"graph","created_at":"2026-05-18T02:44:31Z","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":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance."}],"snapshot_sha256":"d1b44a6b88d31c59a5dfb144f0bff82c76a3e6e5440c0138f5524f9f6b3f8c49"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1e466faa7fe7dcf62506c25e1f9c907ee62368e8f0650c45986e6920b5b7af44"},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOP","authors_text":"Lang Cao, Shengyue Guan, Yihao Liu","cross_cats":[],"headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-07T03:49:25Z","title":"SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management"},"references":{"count":21,"internal_anchors":1,"resolved_work":21,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Smart routing for sustainable supply chain net- works: An ai and knowledge graph driven approach. Applied Sciences, 15(14):8001. Elizabeth Fons, Rachneet Kaur, Soham Palande, Zhen Zeng, Tucker Balch, ","work_id":"9bb80603-0f99-4cf7-a321-48890f9836db","year":2024},{"cited_arxiv_id":"2503.21460","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","work_id":"4aff48d9-c46d-41d9-904b-52251e559596","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Identifier Extraction:The system first parses the user’s query to extract the primary trade_order_id","work_id":"387b9cb7-30c9-4c4d-bf40-efa410e3b2ce","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"An order may be split into multiple fulfillments","work_id":"f50b75f3-3350-4797-940f-f7a269c37a8d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Status Check:For each fulfillment_id iden- tified in the previous step, the system queries its real-time status","work_id":"5b2d833a-6d72-41fa-823c-caa82a1f9dcb","year":null}],"snapshot_sha256":"f91a2040f821c20cba4d2e477d167512e1f1f3a0db466929ade5c0742b69753b"},"source":{"id":"2602.07342","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T06:46:48.786277Z","id":"ca4685e4-28ca-4376-a74f-9019257a588c","model_set":{"reader":"grok-4.3"},"one_line_summary":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","strongest_claim":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance.","weakest_assumption":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested."}},"verdict_id":"ca4685e4-28ca-4376-a74f-9019257a588c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:48defddee6b3b14f3f519b1712f81e6185e7828c28e85d8aac0d1cefa3669b7f","target":"record","created_at":"2026-05-18T02:44:31Z","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":"09ff1b7536411fbd75f17ff9bc5c672c9dfa972c99eb2bf34a0cdced8bd6547f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-07T03:49:25Z","title_canon_sha256":"48aa46042a6438d3916f11b3dbfb88c2a0f3820fab4d91a479b86bc9968306e7"},"schema_version":"1.0","source":{"id":"2602.07342","kind":"arxiv","version":2}},"canonical_sha256":"5e0290205ac9ae58fef4a426940e8316cf97059127a3d16179cc94be8ac488b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e0290205ac9ae58fef4a426940e8316cf97059127a3d16179cc94be8ac488b5","first_computed_at":"2026-05-18T02:44:31.322406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:31.322406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KYyjXwI7F4PPYo8eQcMY/5wFH/LYCOqcClVJ0/feZqgvFdmmAmFjSLgy9XjzvCuhmW6LJamEY8+27mh6WG+QDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:31.322930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48defddee6b3b14f3f519b1712f81e6185e7828c28e85d8aac0d1cefa3669b7f","sha256:a91498a31f128f582cba399261f7e6ba2876ac87f93446eef8c944d2f5b7729a"],"state_sha256":"7b797a2c80cfeddaa4af00f361da8b4cd15dec2533f4a06a8d537a27cea71eef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Nijt9FgIAiUZrQYfAzQ0FQ8d2+Up/E2VotheDU8V4t8K6f59V/t3wsD+ZThFwmNaZEr3Wz8+Y5ohBCZjTwBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:49:42.028833Z","bundle_sha256":"33c4880ae32d3b3892c068cbc412fb73ce295e53eca192aa0b6fc54fdb60ece0"}}