{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UGQ7E5KGSNNFW4FY4TIA7IHL6Y","short_pith_number":"pith:UGQ7E5KG","schema_version":"1.0","canonical_sha256":"a1a1f27546935a5b70b8e4d00fa0ebf621475ce4ba625db5ff6b61c6a19d595b","source":{"kind":"arxiv","id":"2510.14828","version":3},"attestation_state":"computed","paper":{"title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bingyan Nie, Boyu Li, Haoran Li, Jinrui Liu, Shunsen He, Yaran Chen, Yuze Wang","submitted_at":"2025-10-16T16:04:35Z","abstract_excerpt":"Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large language models and vision language models based on Supervised Fine-Tuning (SFT) in planning tasks, they continue facing challenges in performing long-horizon manipulation tasks in complex real-world environments, owing to their restricted common sense and reasoning capabilities. Considering that aligning general-purpose vision language models to robotic planning tasks via supervised fine-tuning suffers f"},"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":"2510.14828","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-16T16:04:35Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b5747d266178acd92ef2736750307939447392661e638bec5764c462d1461a11","abstract_canon_sha256":"020912ef26925b8e46841a59e92b70eb4ceb855bdbe5f18efc43afae539e771a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:57.307879Z","signature_b64":"QVRwunFhaVg7MpdrA+1BneTJc8hJ2EDTg2mml9ENI5uFbRHu1PXrZ3mq27Rve8+N9x48AHizPjtkfrSkhMb+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1a1f27546935a5b70b8e4d00fa0ebf621475ce4ba625db5ff6b61c6a19d595b","last_reissued_at":"2026-06-10T01:10:57.306738Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:57.306738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bingyan Nie, Boyu Li, Haoran Li, Jinrui Liu, Shunsen He, Yaran Chen, Yuze Wang","submitted_at":"2025-10-16T16:04:35Z","abstract_excerpt":"Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large language models and vision language models based on Supervised Fine-Tuning (SFT) in planning tasks, they continue facing challenges in performing long-horizon manipulation tasks in complex real-world environments, owing to their restricted common sense and reasoning capabilities. Considering that aligning general-purpose vision language models to robotic planning tasks via supervised fine-tuning suffers f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14828","kind":"arxiv","version":3},"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/2510.14828/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":"2510.14828","created_at":"2026-06-10T01:10:57.306894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14828v3","created_at":"2026-06-10T01:10:57.306894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14828","created_at":"2026-06-10T01:10:57.306894+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGQ7E5KGSNNF","created_at":"2026-06-10T01:10:57.306894+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGQ7E5KGSNNFW4FY","created_at":"2026-06-10T01:10:57.306894+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGQ7E5KG","created_at":"2026-06-10T01:10:57.306894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.13775","citing_title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y","json":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y.json","graph_json":"https://pith.science/api/pith-number/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/graph.json","events_json":"https://pith.science/api/pith-number/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/events.json","paper":"https://pith.science/paper/UGQ7E5KG"},"agent_actions":{"view_html":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y","download_json":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y.json","view_paper":"https://pith.science/paper/UGQ7E5KG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14828&json=true","fetch_graph":"https://pith.science/api/pith-number/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/action/storage_attestation","attest_author":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/action/author_attestation","sign_citation":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/action/citation_signature","submit_replication":"https://pith.science/pith/UGQ7E5KGSNNFW4FY4TIA7IHL6Y/action/replication_record"}},"created_at":"2026-06-10T01:10:57.306894+00:00","updated_at":"2026-06-10T01:10:57.306894+00:00"}