{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q6MT36L3AGM6RRK7DDN6YXZBYF","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":"6f6eac1e703eecd6aebcb7e16d76b34db56ffab0a237c73ff9d20fb8e9c16ec6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T13:37:47Z","title_canon_sha256":"f252f1ed6d6d84f8d3e5a885286683aad4e2edb06dfdb6a35f0484a7c1fc0d19"},"schema_version":"1.0","source":{"id":"2606.04874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04874","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04874v1","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04874","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"Q6MT36L3AGM6","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"Q6MT36L3AGM6RRK7","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"Q6MT36L3","created_at":"2026-06-04T01:09:52Z"}],"graph_snapshots":[{"event_id":"sha256:5e7c961272f07d31c60923a153da51b433f432e3c608954445b5fde3e991a9e3","target":"graph","created_at":"2026-06-04T01:09:52Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.04874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible. Yet existing agent evaluations often report only end-to-end success, making it difficult to determine whether failures stem from planning or execution. We introduce \\textbf{Agent Planning Benchmark (APB)}, a planning-specific diagnostic benchmark with 4,209 multimodal cases across 22 domains and five settings, covering holistic planning, feedback-conditioned step-wise planning, and robustness under extraneous tools, broken tools, and unso","authors_text":"Haoyu Sun, Jujie He, Mingyang Song, Weinan Zhang, Wenxuan Wang, Yang Liu, Yang Yang, Yu Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T13:37:47Z","title":"Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04874","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d694717b64ed8a841825c7029222e785ea85037423d57998e74e6f9ef661436","target":"record","created_at":"2026-06-04T01:09:52Z","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":"6f6eac1e703eecd6aebcb7e16d76b34db56ffab0a237c73ff9d20fb8e9c16ec6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T13:37:47Z","title_canon_sha256":"f252f1ed6d6d84f8d3e5a885286683aad4e2edb06dfdb6a35f0484a7c1fc0d19"},"schema_version":"1.0","source":{"id":"2606.04874","kind":"arxiv","version":1}},"canonical_sha256":"87993df97b0199e8c55f18dbec5f21c154650e9ffff68dc2d84466a455963dae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87993df97b0199e8c55f18dbec5f21c154650e9ffff68dc2d84466a455963dae","first_computed_at":"2026-06-04T01:09:52.773005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:52.773005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUYwq0XyrreT4fRzALOifXtiPNZrnblgZu/unMOZBe0vkaXzEevUGsV/Auzn4fnVVLwwtB2yGV0TIu8HL+vPBg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:52.774014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d694717b64ed8a841825c7029222e785ea85037423d57998e74e6f9ef661436","sha256:5e7c961272f07d31c60923a153da51b433f432e3c608954445b5fde3e991a9e3"],"state_sha256":"8359d4babf9de25c7a453283884357c082a24f642654178e23396e232d9b1cd9"}