{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OFRLEMYZBIU6DD5IYL3NQW7MY","short_pith_number":"pith:3OFRLEMY","schema_version":"1.0","canonical_sha256":"db8b159198c8514f0c7d4617b6c2df663de75d240aa228c0d4f6f52e44636659","source":{"kind":"arxiv","id":"2305.13536","version":3},"attestation_state":"computed","paper":{"title":"Subspace-Configurable Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Wang, Lothar Thiele, Olga Saukh, Xiaoxi He","submitted_at":"2023-05-22T23:19:45Z","abstract_excerpt":"While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to what was used during offline training due to factors such as specific sensor placement or naturally changing sensing conditions. Hence, achieving the desired robustness necessitates the utilization of either an invariant architecture or specialized training approaches, like data augmentation techniques. Alternatively, input transformations can be treated as a d"},"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":"2305.13536","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T23:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"8f3c805e189379e0872e8babf1869f570640ba3688a45d83d28585b035bf4a22","abstract_canon_sha256":"30df582a1a60c6952bc08d0fb5dd4ba84f864c90dd130d96535d92999cefd8ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:53.613977Z","signature_b64":"NoRZsFRiazf2p4F7OrER10luyYkpG4c4aKSI7fjP4TSrVRQAb1yZG5L3Edlwboe03o+YlXtduTyPhz/aFdFuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8b159198c8514f0c7d4617b6c2df663de75d240aa228c0d4f6f52e44636659","last_reissued_at":"2026-07-05T08:23:53.613453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:53.613453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subspace-Configurable Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Wang, Lothar Thiele, Olga Saukh, Xiaoxi He","submitted_at":"2023-05-22T23:19:45Z","abstract_excerpt":"While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to what was used during offline training due to factors such as specific sensor placement or naturally changing sensing conditions. Hence, achieving the desired robustness necessitates the utilization of either an invariant architecture or specialized training approaches, like data augmentation techniques. Alternatively, input transformations can be treated as a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13536","kind":"arxiv","version":3},"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/2305.13536/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":"2305.13536","created_at":"2026-07-05T08:23:53.613511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13536v3","created_at":"2026-07-05T08:23:53.613511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13536","created_at":"2026-07-05T08:23:53.613511+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OFRLEMYZBIU","created_at":"2026-07-05T08:23:53.613511+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OFRLEMYZBIU6DD5","created_at":"2026-07-05T08:23:53.613511+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OFRLEMY","created_at":"2026-07-05T08:23:53.613511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23536","citing_title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY","json":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY.json","graph_json":"https://pith.science/api/pith-number/3OFRLEMYZBIU6DD5IYL3NQW7MY/graph.json","events_json":"https://pith.science/api/pith-number/3OFRLEMYZBIU6DD5IYL3NQW7MY/events.json","paper":"https://pith.science/paper/3OFRLEMY"},"agent_actions":{"view_html":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY","download_json":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY.json","view_paper":"https://pith.science/paper/3OFRLEMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13536&json=true","fetch_graph":"https://pith.science/api/pith-number/3OFRLEMYZBIU6DD5IYL3NQW7MY/graph.json","fetch_events":"https://pith.science/api/pith-number/3OFRLEMYZBIU6DD5IYL3NQW7MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY/action/storage_attestation","attest_author":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY/action/author_attestation","sign_citation":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY/action/citation_signature","submit_replication":"https://pith.science/pith/3OFRLEMYZBIU6DD5IYL3NQW7MY/action/replication_record"}},"created_at":"2026-07-05T08:23:53.613511+00:00","updated_at":"2026-07-05T08:23:53.613511+00:00"}