{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HD3ORU72E3X5VS52ZW7SNGUB7R","short_pith_number":"pith:HD3ORU72","schema_version":"1.0","canonical_sha256":"38f6e8d3fa26efdacbbacdbf269a81fc4a10f9380014eb98b104507386895ca5","source":{"kind":"arxiv","id":"2409.20537","version":1},"attestation_state":"computed","paper":{"title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jialiang Zhao, Kaiming He, Lirui Wang, Xinlei Chen","submitted_at":"2024-09-30T17:39:41Z","abstract_excerpt":"One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This work studies the problem of learning policy representations through heterogeneous pre-training on robot data across different embodiments and tasks at scale. We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a large, shareable trunk of a policy neural network to learn a task and embodiment agnostic shared representation. This general arc"},"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":"2409.20537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-30T17:39:41Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b47251ceb67e4a4762a09215d0ff6952eb57f7384624fa4f21a0f03471082436","abstract_canon_sha256":"e18395b8d3e4fdfdf729d7469214ee80a702249528789e9f7e7a60eb865f1a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:44.965781Z","signature_b64":"Y5Q8C0QOem4QWjIRiBW0D0XX/BDoLvlkMfaU5GYb3OcapaHZ/MQplsuboULnePea2RqH4QiyBfPLkZHIglEQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f6e8d3fa26efdacbbacdbf269a81fc4a10f9380014eb98b104507386895ca5","last_reissued_at":"2026-07-05T09:13:44.965357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:44.965357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jialiang Zhao, Kaiming He, Lirui Wang, Xinlei Chen","submitted_at":"2024-09-30T17:39:41Z","abstract_excerpt":"One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This work studies the problem of learning policy representations through heterogeneous pre-training on robot data across different embodiments and tasks at scale. We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a large, shareable trunk of a policy neural network to learn a task and embodiment agnostic shared representation. This general arc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20537","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/2409.20537/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":"2409.20537","created_at":"2026-07-05T09:13:44.965410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20537v1","created_at":"2026-07-05T09:13:44.965410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20537","created_at":"2026-07-05T09:13:44.965410+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD3ORU72E3X5","created_at":"2026-07-05T09:13:44.965410+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD3ORU72E3X5VS52","created_at":"2026-07-05T09:13:44.965410+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD3ORU72","created_at":"2026-07-05T09:13:44.965410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08436","citing_title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":9,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02739","citing_title":"Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07607","citing_title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R","json":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R.json","graph_json":"https://pith.science/api/pith-number/HD3ORU72E3X5VS52ZW7SNGUB7R/graph.json","events_json":"https://pith.science/api/pith-number/HD3ORU72E3X5VS52ZW7SNGUB7R/events.json","paper":"https://pith.science/paper/HD3ORU72"},"agent_actions":{"view_html":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R","download_json":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R.json","view_paper":"https://pith.science/paper/HD3ORU72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20537&json=true","fetch_graph":"https://pith.science/api/pith-number/HD3ORU72E3X5VS52ZW7SNGUB7R/graph.json","fetch_events":"https://pith.science/api/pith-number/HD3ORU72E3X5VS52ZW7SNGUB7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R/action/storage_attestation","attest_author":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R/action/author_attestation","sign_citation":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R/action/citation_signature","submit_replication":"https://pith.science/pith/HD3ORU72E3X5VS52ZW7SNGUB7R/action/replication_record"}},"created_at":"2026-07-05T09:13:44.965410+00:00","updated_at":"2026-07-05T09:13:44.965410+00:00"}