{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AEQDXMZSONWRHPPM6WONSRLTEQ","short_pith_number":"pith:AEQDXMZS","schema_version":"1.0","canonical_sha256":"01203bb332736d13bdecf59cd9457324034b4d3a16f4a9716760f89a75d8cf72","source":{"kind":"arxiv","id":"2606.28529","version":1},"attestation_state":"computed","paper":{"title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Hongyang Jia, Huazhong Yang, Junli Chen, Shunan Dong, Yixuan Li, Yongpan Liu, Yujin Wang","submitted_at":"2026-06-26T18:28:52Z","abstract_excerpt":"Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization, pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-step computation cost and inter-action latency. However, unlike traditional static ML tasks, embodied tasks involve repeated interaction with the environment, and task-level performance is determined not only by per-step cost, but also by closed-loop effects unique to embodied execution, which remai"},"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":"2606.28529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-26T18:28:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3cb435cac3c7009bd0328b87aa3fb7bb11ce6e9d0e5a88d6a2e7c20d4b807860","abstract_canon_sha256":"699084bf3b6167ede8778448a59f68a8c08d2f52e3854a1c66c442ad1a53943a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:17.058725Z","signature_b64":"0rrg50yQ0IGzwGLEaW8gg/xdtQ4URQ6OyOxzCa66DqP64DTKAH95qXflVlUSnx2DjdYrgzcg07NKjg4Qs4vUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01203bb332736d13bdecf59cd9457324034b4d3a16f4a9716760f89a75d8cf72","last_reissued_at":"2026-06-30T00:15:17.058260Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:17.058260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Hongyang Jia, Huazhong Yang, Junli Chen, Shunan Dong, Yixuan Li, Yongpan Liu, Yujin Wang","submitted_at":"2026-06-26T18:28:52Z","abstract_excerpt":"Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization, pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-step computation cost and inter-action latency. However, unlike traditional static ML tasks, embodied tasks involve repeated interaction with the environment, and task-level performance is determined not only by per-step cost, but also by closed-loop effects unique to embodied execution, which remai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28529","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/2606.28529/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":"2606.28529","created_at":"2026-06-30T00:15:17.058324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28529v1","created_at":"2026-06-30T00:15:17.058324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28529","created_at":"2026-06-30T00:15:17.058324+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEQDXMZSONWR","created_at":"2026-06-30T00:15:17.058324+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEQDXMZSONWRHPPM","created_at":"2026-06-30T00:15:17.058324+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEQDXMZS","created_at":"2026-06-30T00:15:17.058324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ","json":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ.json","graph_json":"https://pith.science/api/pith-number/AEQDXMZSONWRHPPM6WONSRLTEQ/graph.json","events_json":"https://pith.science/api/pith-number/AEQDXMZSONWRHPPM6WONSRLTEQ/events.json","paper":"https://pith.science/paper/AEQDXMZS"},"agent_actions":{"view_html":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ","download_json":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ.json","view_paper":"https://pith.science/paper/AEQDXMZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28529&json=true","fetch_graph":"https://pith.science/api/pith-number/AEQDXMZSONWRHPPM6WONSRLTEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AEQDXMZSONWRHPPM6WONSRLTEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ/action/storage_attestation","attest_author":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ/action/author_attestation","sign_citation":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ/action/citation_signature","submit_replication":"https://pith.science/pith/AEQDXMZSONWRHPPM6WONSRLTEQ/action/replication_record"}},"created_at":"2026-06-30T00:15:17.058324+00:00","updated_at":"2026-06-30T00:15:17.058324+00:00"}