{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ITAMAUPAWUIFQZ77GLV6LWNC5","short_pith_number":"pith:7ITAMAUP","schema_version":"1.0","canonical_sha256":"fa2606028f05a882c33ff9975f2ecd1762726c62c3922b799a5069115a379788","source":{"kind":"arxiv","id":"2509.08500","version":1},"attestation_state":"computed","paper":{"title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bei Li, Jiahao Liu, Jingang Wang, Junhao Ruan, Kechen Jiao, Qifan Wang, Xinyu Liu, Xiu Li, Yaxin Xu, Yifan Zhu, Zhirui Fang, Zhongjian Qiao","submitted_at":"2025-09-10T11:16:21Z","abstract_excerpt":"Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with the real physical world, they still exhibit sluggish responses and hallucination issues in dynamically changing environments, necessitating further alignment. Existing post-SFT methods, reliant on reinforcement learning and chain-of-thought (CoT) approaches, are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, "},"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":"2509.08500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-10T11:16:21Z","cross_cats_sorted":[],"title_canon_sha256":"81ffb93f9f163a7fee64f275d29bc21983a94125eb3d89a756159e547c34422f","abstract_canon_sha256":"300e0c0006130a8635e57b9bda98bb55234220b21ec1390121e578e4e5c1857d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:31.223993Z","signature_b64":"Z2TnsTKfsgcXkJxnkoFzsAIis/Mxzu/ja6IsC+j5JROQCx7ogCYjTz+xkm5n+6SONS2l67qLOhLGOBAAOVtcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa2606028f05a882c33ff9975f2ecd1762726c62c3922b799a5069115a379788","last_reissued_at":"2026-07-05T12:08:31.223505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:31.223505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bei Li, Jiahao Liu, Jingang Wang, Junhao Ruan, Kechen Jiao, Qifan Wang, Xinyu Liu, Xiu Li, Yaxin Xu, Yifan Zhu, Zhirui Fang, Zhongjian Qiao","submitted_at":"2025-09-10T11:16:21Z","abstract_excerpt":"Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with the real physical world, they still exhibit sluggish responses and hallucination issues in dynamically changing environments, necessitating further alignment. Existing post-SFT methods, reliant on reinforcement learning and chain-of-thought (CoT) approaches, are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08500","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/2509.08500/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":"2509.08500","created_at":"2026-07-05T12:08:31.223564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08500v1","created_at":"2026-07-05T12:08:31.223564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08500","created_at":"2026-07-05T12:08:31.223564+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ITAMAUPAWUI","created_at":"2026-07-05T12:08:31.223564+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ITAMAUPAWUIFQZ7","created_at":"2026-07-05T12:08:31.223564+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ITAMAUP","created_at":"2026-07-05T12:08:31.223564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5","json":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5.json","graph_json":"https://pith.science/api/pith-number/7ITAMAUPAWUIFQZ77GLV6LWNC5/graph.json","events_json":"https://pith.science/api/pith-number/7ITAMAUPAWUIFQZ77GLV6LWNC5/events.json","paper":"https://pith.science/paper/7ITAMAUP"},"agent_actions":{"view_html":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5","download_json":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5.json","view_paper":"https://pith.science/paper/7ITAMAUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08500&json=true","fetch_graph":"https://pith.science/api/pith-number/7ITAMAUPAWUIFQZ77GLV6LWNC5/graph.json","fetch_events":"https://pith.science/api/pith-number/7ITAMAUPAWUIFQZ77GLV6LWNC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5/action/storage_attestation","attest_author":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5/action/author_attestation","sign_citation":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5/action/citation_signature","submit_replication":"https://pith.science/pith/7ITAMAUPAWUIFQZ77GLV6LWNC5/action/replication_record"}},"created_at":"2026-07-05T12:08:31.223564+00:00","updated_at":"2026-07-05T12:08:31.223564+00:00"}