{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:74DYU24LOKV4FRZ3EZ5O3YLUIB","short_pith_number":"pith:74DYU24L","schema_version":"1.0","canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","source":{"kind":"arxiv","id":"2501.18867","version":3},"attestation_state":"computed","paper":{"title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianke Zhang, Jianyu Chen, Xiang Zhu, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","submitted_at":"2025-01-31T03:20:09Z","abstract_excerpt":"Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich semantic knowledge and reasoning abilities. However, prior research has shown that VLMs often focus on high-level semantic content and neglect low-level features, limiting their ability to capture detailed spatial information and understand physical dynamics. These aspects, which are crucial for embodied control tasks, remain underexplored in existing pre-t"},"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":"2501.18867","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09ecedf72a1981b181d96a35ec4dd501e7ed50301eaa757f3e9e512f60e9fee5","abstract_canon_sha256":"29fe6781ccdd5e088272c3dd956c7b6fa8144dd69137baf3bb8218e7f233afc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:23.680840Z","signature_b64":"+BWMRb9DGqKyUR4FKJgUIL14hvuBLO+GcDIR9X2S0Zrb+mYJ9lWOYJJQjmFLrlvd+BgFCtBmmFvDyVLdVrn2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","last_reissued_at":"2026-07-05T11:27:23.680332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:23.680332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianke Zhang, Jianyu Chen, Xiang Zhu, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","submitted_at":"2025-01-31T03:20:09Z","abstract_excerpt":"Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich semantic knowledge and reasoning abilities. However, prior research has shown that VLMs often focus on high-level semantic content and neglect low-level features, limiting their ability to capture detailed spatial information and understand physical dynamics. These aspects, which are crucial for embodied control tasks, remain underexplored in existing pre-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18867","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/2501.18867/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":"2501.18867","created_at":"2026-07-05T11:27:23.680393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18867v3","created_at":"2026-07-05T11:27:23.680393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18867","created_at":"2026-07-05T11:27:23.680393+00:00"},{"alias_kind":"pith_short_12","alias_value":"74DYU24LOKV4","created_at":"2026-07-05T11:27:23.680393+00:00"},{"alias_kind":"pith_short_16","alias_value":"74DYU24LOKV4FRZ3","created_at":"2026-07-05T11:27:23.680393+00:00"},{"alias_kind":"pith_short_8","alias_value":"74DYU24L","created_at":"2026-07-05T11:27:23.680393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21088","citing_title":"MV-WAM: Manifold-Aware World Action Model with Value Augmentation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12403","citing_title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06155","citing_title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29384","citing_title":"Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28548","citing_title":"GEM: Generative Supervision Helps Embodied Intelligence","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20200","citing_title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15735","citing_title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09928","citing_title":"HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07931","citing_title":"One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25661","citing_title":"Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26320","citing_title":"DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10819","citing_title":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07931","citing_title":"One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10821","citing_title":"UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10819","citing_title":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07931","citing_title":"One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB","json":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB.json","graph_json":"https://pith.science/api/pith-number/74DYU24LOKV4FRZ3EZ5O3YLUIB/graph.json","events_json":"https://pith.science/api/pith-number/74DYU24LOKV4FRZ3EZ5O3YLUIB/events.json","paper":"https://pith.science/paper/74DYU24L"},"agent_actions":{"view_html":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB","download_json":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB.json","view_paper":"https://pith.science/paper/74DYU24L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18867&json=true","fetch_graph":"https://pith.science/api/pith-number/74DYU24LOKV4FRZ3EZ5O3YLUIB/graph.json","fetch_events":"https://pith.science/api/pith-number/74DYU24LOKV4FRZ3EZ5O3YLUIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/action/storage_attestation","attest_author":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/action/author_attestation","sign_citation":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/action/citation_signature","submit_replication":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/action/replication_record"}},"created_at":"2026-07-05T11:27:23.680393+00:00","updated_at":"2026-07-05T11:27:23.680393+00:00"}