{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W25MSGKITWKZCMNEGFP5XNK4JY","short_pith_number":"pith:W25MSGKI","schema_version":"1.0","canonical_sha256":"b6bac919489d959131a4315fdbb55c4e18d7a07a6ca824e04faa04de4b4659a7","source":{"kind":"arxiv","id":"2512.24125","version":3},"attestation_state":"computed","paper":{"title":"Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chuankang Li, Dafeng Wei, Guanghui Ren, Jiange Yang, Jianlan Luo, Jinyu Zhang, Liliang Chen, Linqing Zhong, Maoqing Yao, Sukai Wang, Xiaowei Cai, Xindong He, Yi Liu","submitted_at":"2025-12-30T10:18:42Z","abstract_excerpt":"General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models. While large Vision-Language Models (VLMs) improve semantic generalization, insufficient embodied reasoning leads to brittle behavior, and conversely, strong reasoning alone is inadequate without precise control. To provide a decoupled and quantitative assessment of this bottleneck, we introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodie"},"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":"2512.24125","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-30T10:18:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93de029c80568000677b47c1a9622a14ae93d27c7720f858c2d73ffa3003e930","abstract_canon_sha256":"6dfa120e76a2f445bba950845af06085dbe621f282338fde9ba9223d08929581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:27.127243Z","signature_b64":"n5kFcrN/lLuXNU2Juva6gqfSURHmy2Q2VwuyOgOswhjSqm6eoX4TJSCf58fpOWt56IHOiyAPuNouYWd06A1dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6bac919489d959131a4315fdbb55c4e18d7a07a6ca824e04faa04de4b4659a7","last_reissued_at":"2026-07-28T01:22:27.126383Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:27.126383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chuankang Li, Dafeng Wei, Guanghui Ren, Jiange Yang, Jianlan Luo, Jinyu Zhang, Liliang Chen, Linqing Zhong, Maoqing Yao, Sukai Wang, Xiaowei Cai, Xindong He, Yi Liu","submitted_at":"2025-12-30T10:18:42Z","abstract_excerpt":"General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models. While large Vision-Language Models (VLMs) improve semantic generalization, insufficient embodied reasoning leads to brittle behavior, and conversely, strong reasoning alone is inadequate without precise control. To provide a decoupled and quantitative assessment of this bottleneck, we introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.24125","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/2512.24125/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":"2512.24125","created_at":"2026-07-28T01:22:27.126791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.24125v3","created_at":"2026-07-28T01:22:27.126791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.24125","created_at":"2026-07-28T01:22:27.126791+00:00"},{"alias_kind":"pith_short_12","alias_value":"W25MSGKITWKZ","created_at":"2026-07-28T01:22:27.126791+00:00"},{"alias_kind":"pith_short_16","alias_value":"W25MSGKITWKZCMNE","created_at":"2026-07-28T01:22:27.126791+00:00"},{"alias_kind":"pith_short_8","alias_value":"W25MSGKI","created_at":"2026-07-28T01:22:27.126791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31196","citing_title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY","json":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY.json","graph_json":"https://pith.science/api/pith-number/W25MSGKITWKZCMNEGFP5XNK4JY/graph.json","events_json":"https://pith.science/api/pith-number/W25MSGKITWKZCMNEGFP5XNK4JY/events.json","paper":"https://pith.science/paper/W25MSGKI"},"agent_actions":{"view_html":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY","download_json":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY.json","view_paper":"https://pith.science/paper/W25MSGKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.24125&json=true","fetch_graph":"https://pith.science/api/pith-number/W25MSGKITWKZCMNEGFP5XNK4JY/graph.json","fetch_events":"https://pith.science/api/pith-number/W25MSGKITWKZCMNEGFP5XNK4JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY/action/storage_attestation","attest_author":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY/action/author_attestation","sign_citation":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY/action/citation_signature","submit_replication":"https://pith.science/pith/W25MSGKITWKZCMNEGFP5XNK4JY/action/replication_record"}},"created_at":"2026-07-28T01:22:27.126791+00:00","updated_at":"2026-07-28T01:22:27.126791+00:00"}