{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORE7X65USUW5I7UNLDTUJV5GHC","short_pith_number":"pith:ORE7X65U","schema_version":"1.0","canonical_sha256":"7449fbfbb4952dd47e8d58e744d7a638a1af998a49ddd38c5f789ce932689d96","source":{"kind":"arxiv","id":"2412.15109","version":1},"attestation_state":"computed","paper":{"title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dahua Lin, Hao Dong, Jiangmiao Pang, Jia Zeng, Ping Wang, Sizhe Yang, Yang Tian","submitted_at":"2024-12-19T17:52:50Z","abstract_excerpt":"Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on \"action,\" which involves behavior cloning from extensive collections of robotic data, while the other emphasizes \"vision,\" enhancing model generalization by pre-training representations or generative models, also referred to as world models, using large-scale visual datasets. This paper presents an end-to-end paradigm that predicts actions using inverse dynamics models conditioned on the robot's forecasted visual states, named Predictive Inverse Dynamics Models (PIDM). By closi"},"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":"2412.15109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-19T17:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"93dcc00eecaf27500583da38440693e125b2a821ad0272d9d3fe252fc67bb77e","abstract_canon_sha256":"431aa93c284fc2f0d469d8850435f01a4c890caf950284350f40a25ff5f7b2c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T14:32:35.313583Z","signature_b64":"0mUgVceBu0PCRZnkBYOA6z9G5WoqDCsZykRYbwblyo420I/g1osztt617KorN/P7B/ZsukvYBG8y44Vetp8tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7449fbfbb4952dd47e8d58e744d7a638a1af998a49ddd38c5f789ce932689d96","last_reissued_at":"2026-05-22T14:32:35.310666Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T14:32:35.310666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dahua Lin, Hao Dong, Jiangmiao Pang, Jia Zeng, Ping Wang, Sizhe Yang, Yang Tian","submitted_at":"2024-12-19T17:52:50Z","abstract_excerpt":"Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on \"action,\" which involves behavior cloning from extensive collections of robotic data, while the other emphasizes \"vision,\" enhancing model generalization by pre-training representations or generative models, also referred to as world models, using large-scale visual datasets. This paper presents an end-to-end paradigm that predicts actions using inverse dynamics models conditioned on the robot's forecasted visual states, named Predictive Inverse Dynamics Models (PIDM). By closi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15109","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/2412.15109/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":"2412.15109","created_at":"2026-05-22T14:32:35.310819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15109v1","created_at":"2026-05-22T14:32:35.310819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15109","created_at":"2026-05-22T14:32:35.310819+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORE7X65USUW5","created_at":"2026-05-22T14:32:35.310819+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORE7X65USUW5I7UN","created_at":"2026-05-22T14:32:35.310819+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORE7X65U","created_at":"2026-05-22T14:32:35.310819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":22,"sample":[{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17016","citing_title":"Interactive Post-Training for Vision-Language-Action Models","ref_index":33,"is_internal_anchor":true},{"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":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2507.12768","citing_title":"AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18960","citing_title":"AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2510.13778","citing_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29844","citing_title":"DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13030","citing_title":"Motus: A Unified Latent Action World Model","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08732","citing_title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05126","citing_title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06067","citing_title":"HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17887","citing_title":"StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC","json":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC.json","graph_json":"https://pith.science/api/pith-number/ORE7X65USUW5I7UNLDTUJV5GHC/graph.json","events_json":"https://pith.science/api/pith-number/ORE7X65USUW5I7UNLDTUJV5GHC/events.json","paper":"https://pith.science/paper/ORE7X65U"},"agent_actions":{"view_html":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC","download_json":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC.json","view_paper":"https://pith.science/paper/ORE7X65U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15109&json=true","fetch_graph":"https://pith.science/api/pith-number/ORE7X65USUW5I7UNLDTUJV5GHC/graph.json","fetch_events":"https://pith.science/api/pith-number/ORE7X65USUW5I7UNLDTUJV5GHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC/action/storage_attestation","attest_author":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC/action/author_attestation","sign_citation":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC/action/citation_signature","submit_replication":"https://pith.science/pith/ORE7X65USUW5I7UNLDTUJV5GHC/action/replication_record"}},"created_at":"2026-05-22T14:32:35.310819+00:00","updated_at":"2026-05-22T14:32:35.310819+00:00"}