{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QJI33DTYNSHMALLSR3KHFEFENA","short_pith_number":"pith:QJI33DTY","schema_version":"1.0","canonical_sha256":"8251bd8e786c8ec02d728ed47290a46823f6a405afa3db0c93352561ef421315","source":{"kind":"arxiv","id":"2606.15753","version":2},"attestation_state":"computed","paper":{"title":"RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengwen Li, Hongyao Tang, Jianye Hao, Linqi Han, Shuoheng Zhang, Xianze Yao, Yan Zheng, Yaoting Huang, Yifu Yuan","submitted_at":"2026-06-14T11:30:42Z","abstract_excerpt":"Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity references remain implicit and ambiguous. This may cause the reasoning process to decouple from visual evidence, entity references to drift across steps, and a causal disconnection between the reasoning trajectory and the final answer, with these problems further amplified in multi-view scenarios due to cro"},"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":"2606.15753","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T11:30:42Z","cross_cats_sorted":[],"title_canon_sha256":"a551cee079babeaa946bfbf763ee404aa3e473aa851aa0cf9b67f103cf1100bf","abstract_canon_sha256":"d07480472c1cfb241dfaa40e72f2ba6ba9943ea5b0c9a80468747106fea4caf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:09.672258Z","signature_b64":"fQGzzX8ypd/8vIio8gs73/uqICQHYKU+RDsNDURtbiq6DYDfD2zg0OyaRiyUVe8R0QUlqUShKCIoYAcasCTpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8251bd8e786c8ec02d728ed47290a46823f6a405afa3db0c93352561ef421315","last_reissued_at":"2026-06-30T02:18:09.671341Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:09.671341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengwen Li, Hongyao Tang, Jianye Hao, Linqi Han, Shuoheng Zhang, Xianze Yao, Yan Zheng, Yaoting Huang, Yifu Yuan","submitted_at":"2026-06-14T11:30:42Z","abstract_excerpt":"Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity references remain implicit and ambiguous. This may cause the reasoning process to decouple from visual evidence, entity references to drift across steps, and a causal disconnection between the reasoning trajectory and the final answer, with these problems further amplified in multi-view scenarios due to cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15753","kind":"arxiv","version":2},"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/2606.15753/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":"2606.15753","created_at":"2026-06-30T02:18:09.671524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.15753v2","created_at":"2026-06-30T02:18:09.671524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15753","created_at":"2026-06-30T02:18:09.671524+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJI33DTYNSHM","created_at":"2026-06-30T02:18:09.671524+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJI33DTYNSHMALLS","created_at":"2026-06-30T02:18:09.671524+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJI33DTY","created_at":"2026-06-30T02:18:09.671524+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/QJI33DTYNSHMALLSR3KHFEFENA","json":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA.json","graph_json":"https://pith.science/api/pith-number/QJI33DTYNSHMALLSR3KHFEFENA/graph.json","events_json":"https://pith.science/api/pith-number/QJI33DTYNSHMALLSR3KHFEFENA/events.json","paper":"https://pith.science/paper/QJI33DTY"},"agent_actions":{"view_html":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA","download_json":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA.json","view_paper":"https://pith.science/paper/QJI33DTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.15753&json=true","fetch_graph":"https://pith.science/api/pith-number/QJI33DTYNSHMALLSR3KHFEFENA/graph.json","fetch_events":"https://pith.science/api/pith-number/QJI33DTYNSHMALLSR3KHFEFENA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA/action/storage_attestation","attest_author":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA/action/author_attestation","sign_citation":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA/action/citation_signature","submit_replication":"https://pith.science/pith/QJI33DTYNSHMALLSR3KHFEFENA/action/replication_record"}},"created_at":"2026-06-30T02:18:09.671524+00:00","updated_at":"2026-06-30T02:18:09.671524+00:00"}