{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UB2PU43ATETMWNI4HXZOETDK3A","short_pith_number":"pith:UB2PU43A","schema_version":"1.0","canonical_sha256":"a074fa73609926cb351c3df2e24c6ad835f6603a75ef3f700de1edacebf05904","source":{"kind":"arxiv","id":"2605.28548","version":1},"attestation_state":"computed","paper":{"title":"GEM: Generative Supervision Helps Embodied Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangguo Li, Diankun Wu, Fangfu Liu, Han Hu, Junliang Ye, Jun Zhu, Ruowen Zhao, Xumin Yu, Yinan Liang, Yongming Rao, Zhengyi Wang, Zuyan Liu","submitted_at":"2026-05-27T14:39:42Z","abstract_excerpt":"Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus of standard text-guided pre-training paradigms and the low-level spatial and physical knowledge critical for execution in embodied environments. In this paper, we introduce GEM, a Generative-supervised Embodied vision-language Model designed to bridge this divide. We propose integrating a depth map generation task directly into the VLM pre-training phase. By"},"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":"2605.28548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T14:39:42Z","cross_cats_sorted":[],"title_canon_sha256":"5affd9a28d0fb1a190ff1030a4e61e7927fc05e7ec094f435c66c0ed7a939721","abstract_canon_sha256":"3936d3377b5a0bd1951e408ba9085c1f1e9c6596d03586bf5a9f73c7b98bb3f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:56.040063Z","signature_b64":"gmYEMXGVaVuSM6DzT2di0zKvYoLOLQSWk8txj7SG48xKyf5pjF1qcPGb5N7zSgNGXKvuVwFdMv8oBF+7V/xoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a074fa73609926cb351c3df2e24c6ad835f6603a75ef3f700de1edacebf05904","last_reissued_at":"2026-05-28T02:04:56.039609Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:56.039609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEM: Generative Supervision Helps Embodied Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangguo Li, Diankun Wu, Fangfu Liu, Han Hu, Junliang Ye, Jun Zhu, Ruowen Zhao, Xumin Yu, Yinan Liang, Yongming Rao, Zhengyi Wang, Zuyan Liu","submitted_at":"2026-05-27T14:39:42Z","abstract_excerpt":"Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus of standard text-guided pre-training paradigms and the low-level spatial and physical knowledge critical for execution in embodied environments. In this paper, we introduce GEM, a Generative-supervised Embodied vision-language Model designed to bridge this divide. We propose integrating a depth map generation task directly into the VLM pre-training phase. By"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28548","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/2605.28548/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":"2605.28548","created_at":"2026-05-28T02:04:56.039668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28548v1","created_at":"2026-05-28T02:04:56.039668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28548","created_at":"2026-05-28T02:04:56.039668+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB2PU43ATETM","created_at":"2026-05-28T02:04:56.039668+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB2PU43ATETMWNI4","created_at":"2026-05-28T02:04:56.039668+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB2PU43A","created_at":"2026-05-28T02:04:56.039668+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/UB2PU43ATETMWNI4HXZOETDK3A","json":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A.json","graph_json":"https://pith.science/api/pith-number/UB2PU43ATETMWNI4HXZOETDK3A/graph.json","events_json":"https://pith.science/api/pith-number/UB2PU43ATETMWNI4HXZOETDK3A/events.json","paper":"https://pith.science/paper/UB2PU43A"},"agent_actions":{"view_html":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A","download_json":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A.json","view_paper":"https://pith.science/paper/UB2PU43A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28548&json=true","fetch_graph":"https://pith.science/api/pith-number/UB2PU43ATETMWNI4HXZOETDK3A/graph.json","fetch_events":"https://pith.science/api/pith-number/UB2PU43ATETMWNI4HXZOETDK3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A/action/storage_attestation","attest_author":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A/action/author_attestation","sign_citation":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A/action/citation_signature","submit_replication":"https://pith.science/pith/UB2PU43ATETMWNI4HXZOETDK3A/action/replication_record"}},"created_at":"2026-05-28T02:04:56.039668+00:00","updated_at":"2026-05-28T02:04:56.039668+00:00"}