{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G7QUFX2ERUJ6HRGI33HXD4PZ5X","short_pith_number":"pith:G7QUFX2E","schema_version":"1.0","canonical_sha256":"37e142df448d13e3c4c8decf71f1f9edf9102defc372e7c99fc4adfb20ed572a","source":{"kind":"arxiv","id":"2502.14563","version":1},"attestation_state":"computed","paper":{"title":"Plan-over-Graph: Towards Parallelable LLM Agent Schedule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hai Zhao, Shiqi Zhang, Xinbei Ma, Zhuosheng Zhang, Zouying Cao","submitted_at":"2025-02-20T13:47:51Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose "},"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":"2502.14563","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-20T13:47:51Z","cross_cats_sorted":[],"title_canon_sha256":"ee10624ddc02f9aeb5e9626b8622c10a1128ae0a1ad855b2d9dbbbbabce7aacb","abstract_canon_sha256":"583e16b7083da1088958e77bf146af88bf8dd1da76a047050d868a48a1e8f7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:29.133583Z","signature_b64":"S5IMAGiAyG+aPLvCAZ2gkTjwIOGQiJvkwXLIBy2NipkAp5dvkkRG9qKf4JLomxE4jBqbZPpu6vflO52UQ/FEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37e142df448d13e3c4c8decf71f1f9edf9102defc372e7c99fc4adfb20ed572a","last_reissued_at":"2026-07-05T10:17:29.133128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:29.133128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan-over-Graph: Towards Parallelable LLM Agent Schedule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hai Zhao, Shiqi Zhang, Xinbei Ma, Zhuosheng Zhang, Zouying Cao","submitted_at":"2025-02-20T13:47:51Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14563","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/2502.14563/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":"2502.14563","created_at":"2026-07-05T10:17:29.133182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14563v1","created_at":"2026-07-05T10:17:29.133182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14563","created_at":"2026-07-05T10:17:29.133182+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7QUFX2ERUJ6","created_at":"2026-07-05T10:17:29.133182+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7QUFX2ERUJ6HRGI","created_at":"2026-07-05T10:17:29.133182+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7QUFX2E","created_at":"2026-07-05T10:17:29.133182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01942","citing_title":"Atomic Task Graph: A Unified Framework for Agentic Planning and Execution","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X","json":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X.json","graph_json":"https://pith.science/api/pith-number/G7QUFX2ERUJ6HRGI33HXD4PZ5X/graph.json","events_json":"https://pith.science/api/pith-number/G7QUFX2ERUJ6HRGI33HXD4PZ5X/events.json","paper":"https://pith.science/paper/G7QUFX2E"},"agent_actions":{"view_html":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X","download_json":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X.json","view_paper":"https://pith.science/paper/G7QUFX2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14563&json=true","fetch_graph":"https://pith.science/api/pith-number/G7QUFX2ERUJ6HRGI33HXD4PZ5X/graph.json","fetch_events":"https://pith.science/api/pith-number/G7QUFX2ERUJ6HRGI33HXD4PZ5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X/action/storage_attestation","attest_author":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X/action/author_attestation","sign_citation":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X/action/citation_signature","submit_replication":"https://pith.science/pith/G7QUFX2ERUJ6HRGI33HXD4PZ5X/action/replication_record"}},"created_at":"2026-07-05T10:17:29.133182+00:00","updated_at":"2026-07-05T10:17:29.133182+00:00"}