{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EUKM5X6COEHT4NPBIBRSTAXJAV","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":"3983881037eb90e421b8da35ba900af749ddcf5b347d48c0a2a250d68bd00d69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T04:18:55Z","title_canon_sha256":"f0356bf868c849bd0f1752b57bdbe94c8ab36389ecfa02a041499109ab0083c8"},"schema_version":"1.0","source":{"id":"2605.30824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30824","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30824v1","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30824","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"EUKM5X6COEHT","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"EUKM5X6COEHT4NPB","created_at":"2026-06-01T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"EUKM5X6C","created_at":"2026-06-01T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:6bed967f994d9ca7fbf465b71957cdc3d337dd898a982e6bc4f16b9d1dd38985","target":"graph","created_at":"2026-06-01T01:03:19Z","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/2605.30824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep research tasks require LLMs to plan what to investigate, retrieve evidence, and synthesize long-form answers across multiple branches of inquiry. Existing training paradigms either rely on short-form verifiable QA as a proxy or optimize monolithic long trajectories, which makes planning and execution difficult to disentangle and yields weak credit assignment for the planning process. We propose DecomposeR, a planner-centric deep research framework that represents research plans as typed directed acyclic graphs (DAGs), allowing planning to be made explicit, structured, and rewardable. We t","authors_text":"Mustafa Anis Hussain, Xinle Wu, Yao Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T04:18:55Z","title":"Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30824","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:c9f7120507accec1469332fb5cd47939926bc1799c7fc33a546796b2916c2a1c","target":"record","created_at":"2026-06-01T01:03:19Z","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":"3983881037eb90e421b8da35ba900af749ddcf5b347d48c0a2a250d68bd00d69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T04:18:55Z","title_canon_sha256":"f0356bf868c849bd0f1752b57bdbe94c8ab36389ecfa02a041499109ab0083c8"},"schema_version":"1.0","source":{"id":"2605.30824","kind":"arxiv","version":1}},"canonical_sha256":"2514cedfc2710f3e35e140632982e9056d638928a642fbe1866329a8e109d296","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2514cedfc2710f3e35e140632982e9056d638928a642fbe1866329a8e109d296","first_computed_at":"2026-06-01T01:03:19.151976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:19.151976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35AO/adOEMmJizS8VsYe59GTAapbxekJD+V0j/C40zMhs44BslyGeVGHqOiczuIL9rT7oW4an8BLPJSwkI3CAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:19.153221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9f7120507accec1469332fb5cd47939926bc1799c7fc33a546796b2916c2a1c","sha256:6bed967f994d9ca7fbf465b71957cdc3d337dd898a982e6bc4f16b9d1dd38985"],"state_sha256":"df976851e25ea4ee1c90dd22319bdd49bebbf4b1d8c8e94bf897d3ad47644b37"}