{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HM236EASBTJ6Y5YW6ALYRRN5AI","short_pith_number":"pith:HM236EAS","schema_version":"1.0","canonical_sha256":"3b35bf10120cd3ec7716f01788c5bd021fe0e25268a1b6728ef1d964d5c0af01","source":{"kind":"arxiv","id":"2010.14406","version":3},"attestation_state":"computed","paper":{"title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Ayzaan Wahid, Dan Duong, Ivan Krasin, Johnny Lee, Jonathan Chien, Jonathan Tompson, Maria Attarian, Pete Florence, Stefan Welker, Travis Armstrong, Vikas Sindhwani","submitted_at":"2020-10-27T16:15:08Z","abstract_excerpt":"Robotic manipulation can be formulated as inducing a sequence of spatial displacements: where the space being moved can encompass an object, part of an object, or end effector. In this work, we propose the Transporter Network, a simple model architecture that rearranges deep features to infer spatial displacements from visual input - which can parameterize robot actions. It makes no assumptions of objectness (e.g. canonical poses, models, or keypoints), it exploits spatial symmetries, and is orders of magnitude more sample efficient than our benchmarked alternatives in learning vision-based ma"},"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":"2010.14406","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-27T16:15:08Z","cross_cats_sorted":[],"title_canon_sha256":"1e2308bbf09724900ac9c99aba4627a1265620d5ecbf12046502ba955518288b","abstract_canon_sha256":"4ecfdb58decec16020bab8c399dcfe39ab1a25f47ad816b2c11a195a9e6c0622"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:18.681018Z","signature_b64":"ESZqqVN2baJEHhK55XDahDK0x9EgqhVNUlpT5ECPmy9faXjxp0FBkRDWv0wZoCgoWXFfH27B55Ef8W+PmMUHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b35bf10120cd3ec7716f01788c5bd021fe0e25268a1b6728ef1d964d5c0af01","last_reissued_at":"2026-07-05T03:46:18.680504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:18.680504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Ayzaan Wahid, Dan Duong, Ivan Krasin, Johnny Lee, Jonathan Chien, Jonathan Tompson, Maria Attarian, Pete Florence, Stefan Welker, Travis Armstrong, Vikas Sindhwani","submitted_at":"2020-10-27T16:15:08Z","abstract_excerpt":"Robotic manipulation can be formulated as inducing a sequence of spatial displacements: where the space being moved can encompass an object, part of an object, or end effector. In this work, we propose the Transporter Network, a simple model architecture that rearranges deep features to infer spatial displacements from visual input - which can parameterize robot actions. It makes no assumptions of objectness (e.g. canonical poses, models, or keypoints), it exploits spatial symmetries, and is orders of magnitude more sample efficient than our benchmarked alternatives in learning vision-based ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14406","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/2010.14406/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":"2010.14406","created_at":"2026-07-05T03:46:18.680557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.14406v3","created_at":"2026-07-05T03:46:18.680557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14406","created_at":"2026-07-05T03:46:18.680557+00:00"},{"alias_kind":"pith_short_12","alias_value":"HM236EASBTJ6","created_at":"2026-07-05T03:46:18.680557+00:00"},{"alias_kind":"pith_short_16","alias_value":"HM236EASBTJ6Y5YW","created_at":"2026-07-05T03:46:18.680557+00:00"},{"alias_kind":"pith_short_8","alias_value":"HM236EAS","created_at":"2026-07-05T03:46:18.680557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23625","citing_title":"Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI","json":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI.json","graph_json":"https://pith.science/api/pith-number/HM236EASBTJ6Y5YW6ALYRRN5AI/graph.json","events_json":"https://pith.science/api/pith-number/HM236EASBTJ6Y5YW6ALYRRN5AI/events.json","paper":"https://pith.science/paper/HM236EAS"},"agent_actions":{"view_html":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI","download_json":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI.json","view_paper":"https://pith.science/paper/HM236EAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.14406&json=true","fetch_graph":"https://pith.science/api/pith-number/HM236EASBTJ6Y5YW6ALYRRN5AI/graph.json","fetch_events":"https://pith.science/api/pith-number/HM236EASBTJ6Y5YW6ALYRRN5AI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI/action/storage_attestation","attest_author":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI/action/author_attestation","sign_citation":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI/action/citation_signature","submit_replication":"https://pith.science/pith/HM236EASBTJ6Y5YW6ALYRRN5AI/action/replication_record"}},"created_at":"2026-07-05T03:46:18.680557+00:00","updated_at":"2026-07-05T03:46:18.680557+00:00"}