{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LY2EVX43IQP65BBAPADWTZTRMM","short_pith_number":"pith:LY2EVX43","schema_version":"1.0","canonical_sha256":"5e344adf9b441fee8420780769e6716300faa94d21a37b6217c50629a91955bd","source":{"kind":"arxiv","id":"2507.07495","version":1},"attestation_state":"computed","paper":{"title":"PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Hamid Palangi, Mihir Parmar, Mingyang Ling, Palash Goyal, Tomas Pfister, Xin Liu, Yiwen Song","submitted_at":"2025-07-10T07:30:44Z","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"},"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":"2507.07495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T07:30:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"544343e89d2428ec13bc4982337bd4ea0cf017efc737edf71a8a453b8e64e97a","abstract_canon_sha256":"43d172a4432a84fdbec1417df6d80c3a93439166a7bd4fa8d68939ddf959da52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:59.309824Z","signature_b64":"7vjTorYlZWvnGKdhk6pBdC5/daDLJzLqOh3K0ehHZ/J0RrBXWZaNWYj0qHbpZkOQAYz01DPE2fT3TGp1YYdpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e344adf9b441fee8420780769e6716300faa94d21a37b6217c50629a91955bd","last_reissued_at":"2026-07-05T11:34:59.309352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:59.309352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Hamid Palangi, Mihir Parmar, Mingyang Ling, Palash Goyal, Tomas Pfister, Xin Liu, Yiwen Song","submitted_at":"2025-07-10T07:30:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07495","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/2507.07495/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":"2507.07495","created_at":"2026-07-05T11:34:59.309411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07495v1","created_at":"2026-07-05T11:34:59.309411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07495","created_at":"2026-07-05T11:34:59.309411+00:00"},{"alias_kind":"pith_short_12","alias_value":"LY2EVX43IQP6","created_at":"2026-07-05T11:34:59.309411+00:00"},{"alias_kind":"pith_short_16","alias_value":"LY2EVX43IQP65BBA","created_at":"2026-07-05T11:34:59.309411+00:00"},{"alias_kind":"pith_short_8","alias_value":"LY2EVX43","created_at":"2026-07-05T11:34:59.309411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00971","citing_title":"CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM","json":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM.json","graph_json":"https://pith.science/api/pith-number/LY2EVX43IQP65BBAPADWTZTRMM/graph.json","events_json":"https://pith.science/api/pith-number/LY2EVX43IQP65BBAPADWTZTRMM/events.json","paper":"https://pith.science/paper/LY2EVX43"},"agent_actions":{"view_html":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM","download_json":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM.json","view_paper":"https://pith.science/paper/LY2EVX43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07495&json=true","fetch_graph":"https://pith.science/api/pith-number/LY2EVX43IQP65BBAPADWTZTRMM/graph.json","fetch_events":"https://pith.science/api/pith-number/LY2EVX43IQP65BBAPADWTZTRMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM/action/storage_attestation","attest_author":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM/action/author_attestation","sign_citation":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM/action/citation_signature","submit_replication":"https://pith.science/pith/LY2EVX43IQP65BBAPADWTZTRMM/action/replication_record"}},"created_at":"2026-07-05T11:34:59.309411+00:00","updated_at":"2026-07-05T11:34:59.309411+00:00"}