{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EFODZ6XEJXA5HNNU4MKEJ5OQ7D","short_pith_number":"pith:EFODZ6XE","schema_version":"1.0","canonical_sha256":"215c3cfae44dc1d3b5b4e31444f5d0f8e5d8665c0c412b0f7daf6f9ef574b3df","source":{"kind":"arxiv","id":"2606.05728","version":1},"attestation_state":"computed","paper":{"title":"DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Yansi Li, Zhuosheng Zhang","submitted_at":"2026-06-04T05:37:31Z","abstract_excerpt":"Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial e"},"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":"2606.05728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T05:37:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d5a7a2703e06c507d4e35823df81055c8017dce2788d487e63fceb4a58884b55","abstract_canon_sha256":"c79c07ec7449794ca94713d291b582bf85f8533c8c5913f9c1b0db45ab9eadaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:00.878893Z","signature_b64":"j6jJRmrCaWFcREtvW3xsUVHHgSZcXUnluXlbvMLc059NKcLHP11Hn2NKCbb2k4WTrj6VgU7KH63ivsGj8FrMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"215c3cfae44dc1d3b5b4e31444f5d0f8e5d8665c0c412b0f7daf6f9ef574b3df","last_reissued_at":"2026-06-05T01:15:00.878396Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:00.878396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Yansi Li, Zhuosheng Zhang","submitted_at":"2026-06-04T05:37:31Z","abstract_excerpt":"Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially large solution space. However, we identify a critical misalignment in predominant approaches: standard autoregressive (AR) decoding suffers from early commitment, where initial token choices rigidly constrain the search trajectory. A controlled study shows that masked denoising raises Pass@10 solution coverage from 0.320 to 0.943 over AR sampling under matched compute. Motivated by this, we propose DiG-Plan, a framework that decouples combinatorial e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05728","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/2606.05728/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":"2606.05728","created_at":"2026-06-05T01:15:00.878486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05728v1","created_at":"2026-06-05T01:15:00.878486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05728","created_at":"2026-06-05T01:15:00.878486+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFODZ6XEJXA5","created_at":"2026-06-05T01:15:00.878486+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFODZ6XEJXA5HNNU","created_at":"2026-06-05T01:15:00.878486+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFODZ6XE","created_at":"2026-06-05T01:15:00.878486+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/EFODZ6XEJXA5HNNU4MKEJ5OQ7D","json":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D.json","graph_json":"https://pith.science/api/pith-number/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/graph.json","events_json":"https://pith.science/api/pith-number/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/events.json","paper":"https://pith.science/paper/EFODZ6XE"},"agent_actions":{"view_html":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D","download_json":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D.json","view_paper":"https://pith.science/paper/EFODZ6XE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05728&json=true","fetch_graph":"https://pith.science/api/pith-number/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/graph.json","fetch_events":"https://pith.science/api/pith-number/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/action/storage_attestation","attest_author":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/action/author_attestation","sign_citation":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/action/citation_signature","submit_replication":"https://pith.science/pith/EFODZ6XEJXA5HNNU4MKEJ5OQ7D/action/replication_record"}},"created_at":"2026-06-05T01:15:00.878486+00:00","updated_at":"2026-06-05T01:15:00.878486+00:00"}