{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LY2EVX43IQP65BBAPADWTZTRMM","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":"43d172a4432a84fdbec1417df6d80c3a93439166a7bd4fa8d68939ddf959da52","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T07:30:44Z","title_canon_sha256":"544343e89d2428ec13bc4982337bd4ea0cf017efc737edf71a8a453b8e64e97a"},"schema_version":"1.0","source":{"id":"2507.07495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07495","created_at":"2026-07-05T11:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07495v1","created_at":"2026-07-05T11:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07495","created_at":"2026-07-05T11:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"LY2EVX43IQP6","created_at":"2026-07-05T11:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"LY2EVX43IQP65BBA","created_at":"2026-07-05T11:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"LY2EVX43","created_at":"2026-07-05T11:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:d221b2a90a36bdffad98afe057e6f40f54de2787185c4306666ff6e9ebca62fc","target":"graph","created_at":"2026-07-05T11:34:59Z","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/2507.07495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such planning structures during post-training to boost the performance of smaller open-source LLMs remains underexplored. Motivated by this, we introduce PLAN-TUNING, a unified post-training framework that (i) distills synthetic task decompositions (termed \"planning trajectories\") from large-scale LLMs and (ii) fine-tunes smaller models via supervised and reinforcemen","authors_text":"Chitta Baral, Hamid Palangi, Mihir Parmar, Mingyang Ling, Palash Goyal, Tomas Pfister, Xin Liu, Yiwen Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T07:30:44Z","title":"PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07495","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":"sha256:8724fd76dc0692cab3a24fb00dd6316f1193bb86cea2a64b28f6dc194fb1226c","target":"record","created_at":"2026-07-05T11:34:59Z","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":"43d172a4432a84fdbec1417df6d80c3a93439166a7bd4fa8d68939ddf959da52","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T07:30:44Z","title_canon_sha256":"544343e89d2428ec13bc4982337bd4ea0cf017efc737edf71a8a453b8e64e97a"},"schema_version":"1.0","source":{"id":"2507.07495","kind":"arxiv","version":1}},"canonical_sha256":"5e344adf9b441fee8420780769e6716300faa94d21a37b6217c50629a91955bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e344adf9b441fee8420780769e6716300faa94d21a37b6217c50629a91955bd","first_computed_at":"2026-07-05T11:34:59.309352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:59.309352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vjTorYlZWvnGKdhk6pBdC5/daDLJzLqOh3K0ehHZ/J0RrBXWZaNWYj0qHbpZkOQAYz01DPE2fT3TGp1YYdpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:59.309824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8724fd76dc0692cab3a24fb00dd6316f1193bb86cea2a64b28f6dc194fb1226c","sha256:d221b2a90a36bdffad98afe057e6f40f54de2787185c4306666ff6e9ebca62fc"],"state_sha256":"0a4bc1557105c813490fcbd4578160d1d4c776f9e7f5ccb6ab778a96692bb997"}