{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6NO472CBXTWG4INZSI3A4UHE5","short_pith_number":"pith:M6NO472C","schema_version":"1.0","canonical_sha256":"679aee7f420de763710dcc91b07287277bd47e1861988ea97dee5b793f4a1a2b","source":{"kind":"arxiv","id":"2412.01034","version":1},"attestation_state":"computed","paper":{"title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Byeongwook Jeon, Hyungmin Kim, Jungwook Choi, JuYoung Yang, Seongmin Park, Wonseok Jeon, Yoonseon Oh","submitted_at":"2024-12-02T01:33:49Z","abstract_excerpt":"Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly increases computational costs, which presents challenges in fields like robot manipulation and autonomous driving that require quick, accurate responses. To address the need for deployment on resource-limited hardware, we propose a new quantization framework for IL-based policy models that fine-tunes parameters to enhance robustness against low-bit precision err"},"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":"2412.01034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-02T01:33:49Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d7d3ca59438942d370a6923c44f90976060b8245b23f34b1576c054b11edf731","abstract_canon_sha256":"e2be98fb499da36070585a2992bf8bd51164d5da34243a3788303fc06d10c710"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:52.508735Z","signature_b64":"Cy0adLfGQCOpZ988kBIEBJ09zqceZ2da+J38iXrDYyDZh8oTksKvk8BghNqAHK3eLHDYeGyrQeXdDEr4I4hZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"679aee7f420de763710dcc91b07287277bd47e1861988ea97dee5b793f4a1a2b","last_reissued_at":"2026-07-05T09:42:52.508200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:52.508200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Byeongwook Jeon, Hyungmin Kim, Jungwook Choi, JuYoung Yang, Seongmin Park, Wonseok Jeon, Yoonseon Oh","submitted_at":"2024-12-02T01:33:49Z","abstract_excerpt":"Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly increases computational costs, which presents challenges in fields like robot manipulation and autonomous driving that require quick, accurate responses. To address the need for deployment on resource-limited hardware, we propose a new quantization framework for IL-based policy models that fine-tunes parameters to enhance robustness against low-bit precision err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01034","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/2412.01034/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":"2412.01034","created_at":"2026-07-05T09:42:52.508263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01034v1","created_at":"2026-07-05T09:42:52.508263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01034","created_at":"2026-07-05T09:42:52.508263+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6NO472CBXTW","created_at":"2026-07-05T09:42:52.508263+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6NO472CBXTWG4IN","created_at":"2026-07-05T09:42:52.508263+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6NO472C","created_at":"2026-07-05T09:42:52.508263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29438","citing_title":"ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14371","citing_title":"OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01581","citing_title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17573","citing_title":"HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5","json":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5.json","graph_json":"https://pith.science/api/pith-number/M6NO472CBXTWG4INZSI3A4UHE5/graph.json","events_json":"https://pith.science/api/pith-number/M6NO472CBXTWG4INZSI3A4UHE5/events.json","paper":"https://pith.science/paper/M6NO472C"},"agent_actions":{"view_html":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5","download_json":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5.json","view_paper":"https://pith.science/paper/M6NO472C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01034&json=true","fetch_graph":"https://pith.science/api/pith-number/M6NO472CBXTWG4INZSI3A4UHE5/graph.json","fetch_events":"https://pith.science/api/pith-number/M6NO472CBXTWG4INZSI3A4UHE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5/action/storage_attestation","attest_author":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5/action/author_attestation","sign_citation":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5/action/citation_signature","submit_replication":"https://pith.science/pith/M6NO472CBXTWG4INZSI3A4UHE5/action/replication_record"}},"created_at":"2026-07-05T09:42:52.508263+00:00","updated_at":"2026-07-05T09:42:52.508263+00:00"}