{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TRPMAAWEG2YNR3UZGNFW6WOHSU","short_pith_number":"pith:TRPMAAWE","schema_version":"1.0","canonical_sha256":"9c5ec002c436b0d8ee99334b6f59c7951286a505a38612923ca62e8c5c33d5d5","source":{"kind":"arxiv","id":"2505.00986","version":3},"attestation_state":"computed","paper":{"title":"EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Ma, Xiao Ma, Young D. Kwon","submitted_at":"2025-05-02T04:19:07Z","abstract_excerpt":"Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techn"},"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":true},"canonical_record":{"source":{"id":"2505.00986","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T04:19:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9b8a3eaa4aee57c958d81c76d8d649bcc5f8376822c7f48e88719265dcdf1abe","abstract_canon_sha256":"9b30579bd8b94cf2d8a5c50cb6be4b0fe31015a0d3c32fe6c10f25051bcbbdd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:49.038984Z","signature_b64":"pTS4rdM1OMCPNs8h8/sfkC8v1EPathxBR2KD/mawJyCE+R5DVKWnCe5FtTRAUzgafFO397kFoeYfPv87Z96sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c5ec002c436b0d8ee99334b6f59c7951286a505a38612923ca62e8c5c33d5d5","last_reissued_at":"2026-06-19T16:09:49.038554Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:49.038554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Ma, Xiao Ma, Young D. Kwon","submitted_at":"2025-05-02T04:19:07Z","abstract_excerpt":"Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techn"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The lightweight domain shift detection mechanism reliably identifies when adaptation is truly needed without missing important shifts or triggering too often on noise.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OD-TTA enables resource-efficient test-time adaptation on edge devices by triggering updates only on detected domain shifts, achieving comparable accuracy with lower energy and computation costs for embodied visual systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d02da766e34a8ec7e37e78594a32f85bfc49e06d9a81c2da1931c9886f3a3ef1"},"source":{"id":"2505.00986","kind":"arxiv","version":3},"verdict":{"id":"6a2ea992-80ea-4483-a931-86bbca8c6896","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-22T16:30:41.202009Z","strongest_claim":"OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.","one_line_summary":"OD-TTA enables resource-efficient test-time adaptation on edge devices by triggering updates only on detected domain shifts, achieving comparable accuracy with lower energy and computation costs for embodied visual systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The lightweight domain shift detection mechanism reliably identifies when adaptation is truly needed without missing important shifts or triggering too often on noise.","pith_extraction_headline":"OD-TTA adapts models on edge devices only when domain shifts are detected, cutting energy use while matching full adaptation accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.00986/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":2,"snapshot_sha256":"ed80b0da352c312e21273503dba6449d8f7403beae54a17e8ebd3f616e3b6138"},"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":"2505.00986","created_at":"2026-06-19T16:09:49.038612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00986v3","created_at":"2026-06-19T16:09:49.038612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00986","created_at":"2026-06-19T16:09:49.038612+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRPMAAWEG2YN","created_at":"2026-06-19T16:09:49.038612+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRPMAAWEG2YNR3UZ","created_at":"2026-06-19T16:09:49.038612+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRPMAAWE","created_at":"2026-06-19T16:09:49.038612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31226","citing_title":"What changes after deployment? A survey on On-device Learning in TinyML","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU","json":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU.json","graph_json":"https://pith.science/api/pith-number/TRPMAAWEG2YNR3UZGNFW6WOHSU/graph.json","events_json":"https://pith.science/api/pith-number/TRPMAAWEG2YNR3UZGNFW6WOHSU/events.json","paper":"https://pith.science/paper/TRPMAAWE"},"agent_actions":{"view_html":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU","download_json":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU.json","view_paper":"https://pith.science/paper/TRPMAAWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00986&json=true","fetch_graph":"https://pith.science/api/pith-number/TRPMAAWEG2YNR3UZGNFW6WOHSU/graph.json","fetch_events":"https://pith.science/api/pith-number/TRPMAAWEG2YNR3UZGNFW6WOHSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU/action/storage_attestation","attest_author":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU/action/author_attestation","sign_citation":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU/action/citation_signature","submit_replication":"https://pith.science/pith/TRPMAAWEG2YNR3UZGNFW6WOHSU/action/replication_record"}},"created_at":"2026-06-19T16:09:49.038612+00:00","updated_at":"2026-06-19T16:09:49.038612+00:00"}