{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HUQXP3KTM2JOGTUYCPCX6AVGRT","short_pith_number":"pith:HUQXP3KT","schema_version":"1.0","canonical_sha256":"3d2177ed536692e34e9813c57f02a68cecd2cf112b91f7dd809f84081221d554","source":{"kind":"arxiv","id":"2410.03132","version":5},"attestation_state":"computed","paper":{"title":"Autoregressive Action Sequence Learning for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Haonan Chang, Liam Schramm, Xinyu Zhang, Yuhan Liu","submitted_at":"2024-10-04T04:07:15Z","abstract_excerpt":"Designing a universal policy architecture that performs well across diverse robots and task configurations remains a key challenge. In this work, we address this by representing robot actions as sequential data and generating actions through autoregressive sequence modeling. Existing autoregressive architectures generate end-effector waypoints sequentially as word tokens in language modeling, which are limited to low-frequency control tasks. Unlike language, robot actions are heterogeneous and often include continuous values -- such as joint positions, 2D pixel coordinates, and end-effector po"},"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":"2410.03132","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-04T04:07:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c304ec232e9fb6b8afd747ba16f2d39bb748f4e78789c9a7c36335e980959bed","abstract_canon_sha256":"873b427b8d85a6ef2c518ffaa684704ea586dd94fc81cf3d059416b242db2811"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:21.553015Z","signature_b64":"qSGFLe8PXE5ZOjNqkn7DWAeYr7rOh+Ftr6a6EfH+fzmRWPyF33wkZrDR8lF8P2WFOzuguw7AyFoJEpUWxXmfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2177ed536692e34e9813c57f02a68cecd2cf112b91f7dd809f84081221d554","last_reissued_at":"2026-07-05T10:39:21.552499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:21.552499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoregressive Action Sequence Learning for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Haonan Chang, Liam Schramm, Xinyu Zhang, Yuhan Liu","submitted_at":"2024-10-04T04:07:15Z","abstract_excerpt":"Designing a universal policy architecture that performs well across diverse robots and task configurations remains a key challenge. In this work, we address this by representing robot actions as sequential data and generating actions through autoregressive sequence modeling. Existing autoregressive architectures generate end-effector waypoints sequentially as word tokens in language modeling, which are limited to low-frequency control tasks. Unlike language, robot actions are heterogeneous and often include continuous values -- such as joint positions, 2D pixel coordinates, and end-effector po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03132","kind":"arxiv","version":5},"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/2410.03132/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":"2410.03132","created_at":"2026-07-05T10:39:21.552562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03132v5","created_at":"2026-07-05T10:39:21.552562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03132","created_at":"2026-07-05T10:39:21.552562+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUQXP3KTM2JO","created_at":"2026-07-05T10:39:21.552562+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUQXP3KTM2JOGTUY","created_at":"2026-07-05T10:39:21.552562+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUQXP3KT","created_at":"2026-07-05T10:39:21.552562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15536","citing_title":"SkiP: When to Skip and When to Refine for Efficient Robot Manipulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10126","citing_title":"AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT","json":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT.json","graph_json":"https://pith.science/api/pith-number/HUQXP3KTM2JOGTUYCPCX6AVGRT/graph.json","events_json":"https://pith.science/api/pith-number/HUQXP3KTM2JOGTUYCPCX6AVGRT/events.json","paper":"https://pith.science/paper/HUQXP3KT"},"agent_actions":{"view_html":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT","download_json":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT.json","view_paper":"https://pith.science/paper/HUQXP3KT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03132&json=true","fetch_graph":"https://pith.science/api/pith-number/HUQXP3KTM2JOGTUYCPCX6AVGRT/graph.json","fetch_events":"https://pith.science/api/pith-number/HUQXP3KTM2JOGTUYCPCX6AVGRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT/action/storage_attestation","attest_author":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT/action/author_attestation","sign_citation":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT/action/citation_signature","submit_replication":"https://pith.science/pith/HUQXP3KTM2JOGTUYCPCX6AVGRT/action/replication_record"}},"created_at":"2026-07-05T10:39:21.552562+00:00","updated_at":"2026-07-05T10:39:21.552562+00:00"}