{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XYDFSQFRKPGFQAPRPZBU6FY5RF","short_pith_number":"pith:XYDFSQFR","schema_version":"1.0","canonical_sha256":"be065940b153cc5801f17e434f171d895bc7c42a52f5766b5a19647c291d78fd","source":{"kind":"arxiv","id":"2607.01942","version":1},"attestation_state":"computed","paper":{"title":"Atomic Task Graph: A Unified Framework for Agentic Planning and Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanyun Cui, Kangye Ji, Sihan Chen, Yue Zhang, Zhi Wang, Ziwen Huang","submitted_at":"2026-07-02T09:34:20Z","abstract_excerpt":"LLM-based agents have shown strong potential for solving complex multi-step tasks, yet existing performance improvements often rely on either scaling to larger backbone models or task-specific fine-tuning. The former incurs substantial computational costs, while the latter typically generalizes poorly across different tasks. Although prompt-based control is training-free and broadly applicable, existing methods still leave input-output dependencies between subtasks implicit in textual trajectories, making verified intermediate results difficult to reuse. To address these limitations, we propos"},"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":"2607.01942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T09:34:20Z","cross_cats_sorted":[],"title_canon_sha256":"01e7b6cf61ad1a2af321d3fe55a63dc610123fafcb0eb4e0f4da3afc0a441cff","abstract_canon_sha256":"9f5b3a85ed2f59608cc197d1f42846cc94fb9a53134935b9149f3b506a26004c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:34.485374Z","signature_b64":"0b2rRzdN//LMt/qo4kzKVGs8TnEns74A3pGEyAxMvGGSUSKRAf3tTufhBF3I46JUZP2SrFVTq+JqqDNqz4uABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be065940b153cc5801f17e434f171d895bc7c42a52f5766b5a19647c291d78fd","last_reissued_at":"2026-07-03T01:17:34.484718Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:34.484718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Atomic Task Graph: A Unified Framework for Agentic Planning and Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanyun Cui, Kangye Ji, Sihan Chen, Yue Zhang, Zhi Wang, Ziwen Huang","submitted_at":"2026-07-02T09:34:20Z","abstract_excerpt":"LLM-based agents have shown strong potential for solving complex multi-step tasks, yet existing performance improvements often rely on either scaling to larger backbone models or task-specific fine-tuning. The former incurs substantial computational costs, while the latter typically generalizes poorly across different tasks. Although prompt-based control is training-free and broadly applicable, existing methods still leave input-output dependencies between subtasks implicit in textual trajectories, making verified intermediate results difficult to reuse. To address these limitations, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01942","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/2607.01942/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":"2607.01942","created_at":"2026-07-03T01:17:34.484827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01942v1","created_at":"2026-07-03T01:17:34.484827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01942","created_at":"2026-07-03T01:17:34.484827+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYDFSQFRKPGF","created_at":"2026-07-03T01:17:34.484827+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYDFSQFRKPGFQAPR","created_at":"2026-07-03T01:17:34.484827+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYDFSQFR","created_at":"2026-07-03T01:17:34.484827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF","json":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF.json","graph_json":"https://pith.science/api/pith-number/XYDFSQFRKPGFQAPRPZBU6FY5RF/graph.json","events_json":"https://pith.science/api/pith-number/XYDFSQFRKPGFQAPRPZBU6FY5RF/events.json","paper":"https://pith.science/paper/XYDFSQFR"},"agent_actions":{"view_html":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF","download_json":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF.json","view_paper":"https://pith.science/paper/XYDFSQFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01942&json=true","fetch_graph":"https://pith.science/api/pith-number/XYDFSQFRKPGFQAPRPZBU6FY5RF/graph.json","fetch_events":"https://pith.science/api/pith-number/XYDFSQFRKPGFQAPRPZBU6FY5RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF/action/storage_attestation","attest_author":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF/action/author_attestation","sign_citation":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF/action/citation_signature","submit_replication":"https://pith.science/pith/XYDFSQFRKPGFQAPRPZBU6FY5RF/action/replication_record"}},"created_at":"2026-07-03T01:17:34.484827+00:00","updated_at":"2026-07-03T01:17:34.484827+00:00"}