{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GB3LHC6SVBYMDM6VQJGDVVGPMB","short_pith_number":"pith:GB3LHC6S","schema_version":"1.0","canonical_sha256":"3076b38bd2a870c1b3d5824c3ad4cf60658f9f02109654432ae65b143ab1f7d9","source":{"kind":"arxiv","id":"2502.18836","version":2},"attestation_state":"computed","paper":{"title":"REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Edward Y. Chang, Longling Geng","submitted_at":"2025-02-26T05:24:22Z","abstract_excerpt":"This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in Real-world planning and scheduling scenarios. The suite encompasses 14 designed planning and scheduling problems that progress from basic to highly complex, incorporating key aspects such as multi-agent coordination, inter-agent dependencies, and dynamic environmental disruptions. Each problem can be scaled along three dimensions: the number of parallel planning threads, the complexity of inter-dependencies, and the frequency of unexpected disruptions requiring Real-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.18836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-26T05:24:22Z","cross_cats_sorted":[],"title_canon_sha256":"e3e3d4e132dda2144c93e0933794da45b0b0755c01f7fb2a67e1308021120fba","abstract_canon_sha256":"3318b2b2d3574e1640b0e2181928f9c0f0d8c46353c6bb76494a18ab4cefc242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:47.762373Z","signature_b64":"YdcDkoxc4FoGiCaU2TyMfAWySp6CxofkjmReBFBmPOAFYzrR91CZrJS4JTNUjnFvNxFGIc4J7qYfFQ/6FCkRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3076b38bd2a870c1b3d5824c3ad4cf60658f9f02109654432ae65b143ab1f7d9","last_reissued_at":"2026-07-05T11:48:47.761809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:47.761809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Edward Y. Chang, Longling Geng","submitted_at":"2025-02-26T05:24:22Z","abstract_excerpt":"This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in Real-world planning and scheduling scenarios. The suite encompasses 14 designed planning and scheduling problems that progress from basic to highly complex, incorporating key aspects such as multi-agent coordination, inter-agent dependencies, and dynamic environmental disruptions. Each problem can be scaled along three dimensions: the number of parallel planning threads, the complexity of inter-dependencies, and the frequency of unexpected disruptions requiring Real-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18836","kind":"arxiv","version":2},"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/2502.18836/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.18836","created_at":"2026-07-05T11:48:47.761903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18836v2","created_at":"2026-07-05T11:48:47.761903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18836","created_at":"2026-07-05T11:48:47.761903+00:00"},{"alias_kind":"pith_short_12","alias_value":"GB3LHC6SVBYM","created_at":"2026-07-05T11:48:47.761903+00:00"},{"alias_kind":"pith_short_16","alias_value":"GB3LHC6SVBYMDM6V","created_at":"2026-07-05T11:48:47.761903+00:00"},{"alias_kind":"pith_short_8","alias_value":"GB3LHC6S","created_at":"2026-07-05T11:48:47.761903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.16120","citing_title":"LLM-Powered AI Agent Systems and Their Applications in Industry","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03409","citing_title":"Robust Agent Compensation (RAC): Teaching AI Agents to Compensate","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02674","citing_title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03409","citing_title":"Robust Agent Compensation (RAC): Teaching AI Agents to Compensate","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB","json":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB.json","graph_json":"https://pith.science/api/pith-number/GB3LHC6SVBYMDM6VQJGDVVGPMB/graph.json","events_json":"https://pith.science/api/pith-number/GB3LHC6SVBYMDM6VQJGDVVGPMB/events.json","paper":"https://pith.science/paper/GB3LHC6S"},"agent_actions":{"view_html":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB","download_json":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB.json","view_paper":"https://pith.science/paper/GB3LHC6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18836&json=true","fetch_graph":"https://pith.science/api/pith-number/GB3LHC6SVBYMDM6VQJGDVVGPMB/graph.json","fetch_events":"https://pith.science/api/pith-number/GB3LHC6SVBYMDM6VQJGDVVGPMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB/action/storage_attestation","attest_author":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB/action/author_attestation","sign_citation":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB/action/citation_signature","submit_replication":"https://pith.science/pith/GB3LHC6SVBYMDM6VQJGDVVGPMB/action/replication_record"}},"created_at":"2026-07-05T11:48:47.761903+00:00","updated_at":"2026-07-05T11:48:47.761903+00:00"}