{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3ZJQE6HKXPD55L6XRZUB3HMZPW","short_pith_number":"pith:3ZJQE6HK","schema_version":"1.0","canonical_sha256":"de530278eabbc7deafd78e681d9d997d8f233e9db8ce51c14c73a541a9d9542d","source":{"kind":"arxiv","id":"2105.06183","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Test-Time Augmentation for Low-Power CPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrea Calimera, Enrico Macii, Luca Mocerino, Roberto G. Rizzo, Valentino Peluso","submitted_at":"2021-05-13T10:50:13Z","abstract_excerpt":"Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effect at inference-time, first running multiple feed-forward passes on a set of altered versions of the same input sample, and then computing the main outcome through a consensus of the aggregated predictions. Unfortunately, the implementation of TTA on"},"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":"2105.06183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-13T10:50:13Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"9223c22ce1d6a9fce8515990c6ff279ee7bb7747606b95ba4b59399760e33acf","abstract_canon_sha256":"9306fec48020efb15b6361a73afb9919eccb6bae20d80e83e71ad7fef50c945c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:05.083071Z","signature_b64":"ndn0c9RuvXuDLPwI4J/xMs0KynEbohcETt2LXyV0n0lnr1+XmWcGeMRom8shfqxv7Db7GNttNYhKkdxVUZ2IBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de530278eabbc7deafd78e681d9d997d8f233e9db8ce51c14c73a541a9d9542d","last_reissued_at":"2026-07-05T02:40:05.082644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:05.082644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Test-Time Augmentation for Low-Power CPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andrea Calimera, Enrico Macii, Luca Mocerino, Roberto G. Rizzo, Valentino Peluso","submitted_at":"2021-05-13T10:50:13Z","abstract_excerpt":"Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effect at inference-time, first running multiple feed-forward passes on a set of altered versions of the same input sample, and then computing the main outcome through a consensus of the aggregated predictions. Unfortunately, the implementation of TTA on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06183","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/2105.06183/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":"2105.06183","created_at":"2026-07-05T02:40:05.082714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.06183v1","created_at":"2026-07-05T02:40:05.082714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06183","created_at":"2026-07-05T02:40:05.082714+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZJQE6HKXPD5","created_at":"2026-07-05T02:40:05.082714+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZJQE6HKXPD55L6X","created_at":"2026-07-05T02:40:05.082714+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZJQE6HK","created_at":"2026-07-05T02:40:05.082714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22764","citing_title":"Test-time augmentation improves efficiency in conformal prediction","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW","json":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW.json","graph_json":"https://pith.science/api/pith-number/3ZJQE6HKXPD55L6XRZUB3HMZPW/graph.json","events_json":"https://pith.science/api/pith-number/3ZJQE6HKXPD55L6XRZUB3HMZPW/events.json","paper":"https://pith.science/paper/3ZJQE6HK"},"agent_actions":{"view_html":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW","download_json":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW.json","view_paper":"https://pith.science/paper/3ZJQE6HK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.06183&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZJQE6HKXPD55L6XRZUB3HMZPW/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZJQE6HKXPD55L6XRZUB3HMZPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW/action/storage_attestation","attest_author":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW/action/author_attestation","sign_citation":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW/action/citation_signature","submit_replication":"https://pith.science/pith/3ZJQE6HKXPD55L6XRZUB3HMZPW/action/replication_record"}},"created_at":"2026-07-05T02:40:05.082714+00:00","updated_at":"2026-07-05T02:40:05.082714+00:00"}