{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZG6KKGSLKIGYEA3NBARYSQXJ3","short_pith_number":"pith:NZG6KKGS","schema_version":"1.0","canonical_sha256":"6e4de528d25a906c101b68411c4a174ed249fbf72b82faacdfb8a170e4565154","source":{"kind":"arxiv","id":"2412.18972","version":1},"attestation_state":"computed","paper":{"title":"Recommending Pre-Trained Models for IoT Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Lugo, Huiyun Peng, Hyeonwoo Heo, James C. Davis, Josh LeBlanc, Kelechi G. Kalu, Lawrence Smith, Nathanael Aou, Parth V. Patil, Wenxin Jiang","submitted_at":"2024-12-25T19:19:55Z","abstract_excerpt":"The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many PTM options for any given task, engineers often find it too costly to evaluate each model's suitability. Approaches such as LogME, LEEP, and ModelSpider help streamline model selection by estimating task relevance without exhaustive tuning. However, these methods largely leave hardware constraints a"},"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":"2412.18972","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T19:19:55Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"60620534ffabee6bc7ee8baa7b3bb84e1f3691cee4dc202906a9fe1ce06f2c5c","abstract_canon_sha256":"87f77a1254f2f2130823d23fab720e9143389368e7491fbe4b2851cd706156d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:14.114953Z","signature_b64":"DrL5KeNczSfWsf2d0QUjkriQBU9ViCtA2g04A6aO2uRVeUr1C92ZKPqa8LUGrf0gYhFMyINK61OTULkPiKIOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e4de528d25a906c101b68411c4a174ed249fbf72b82faacdfb8a170e4565154","last_reissued_at":"2026-07-05T09:54:14.114607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:14.114607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommending Pre-Trained Models for IoT Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Lugo, Huiyun Peng, Hyeonwoo Heo, James C. Davis, Josh LeBlanc, Kelechi G. Kalu, Lawrence Smith, Nathanael Aou, Parth V. Patil, Wenxin Jiang","submitted_at":"2024-12-25T19:19:55Z","abstract_excerpt":"The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many PTM options for any given task, engineers often find it too costly to evaluate each model's suitability. Approaches such as LogME, LEEP, and ModelSpider help streamline model selection by estimating task relevance without exhaustive tuning. However, these methods largely leave hardware constraints a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18972","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/2412.18972/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":"2412.18972","created_at":"2026-07-05T09:54:14.114661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18972v1","created_at":"2026-07-05T09:54:14.114661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18972","created_at":"2026-07-05T09:54:14.114661+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZG6KKGSLKIG","created_at":"2026-07-05T09:54:14.114661+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZG6KKGSLKIGYEA3","created_at":"2026-07-05T09:54:14.114661+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZG6KKGS","created_at":"2026-07-05T09:54:14.114661+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/NZG6KKGSLKIGYEA3NBARYSQXJ3","json":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3.json","graph_json":"https://pith.science/api/pith-number/NZG6KKGSLKIGYEA3NBARYSQXJ3/graph.json","events_json":"https://pith.science/api/pith-number/NZG6KKGSLKIGYEA3NBARYSQXJ3/events.json","paper":"https://pith.science/paper/NZG6KKGS"},"agent_actions":{"view_html":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3","download_json":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3.json","view_paper":"https://pith.science/paper/NZG6KKGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18972&json=true","fetch_graph":"https://pith.science/api/pith-number/NZG6KKGSLKIGYEA3NBARYSQXJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/NZG6KKGSLKIGYEA3NBARYSQXJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3/action/storage_attestation","attest_author":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3/action/author_attestation","sign_citation":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3/action/citation_signature","submit_replication":"https://pith.science/pith/NZG6KKGSLKIGYEA3NBARYSQXJ3/action/replication_record"}},"created_at":"2026-07-05T09:54:14.114661+00:00","updated_at":"2026-07-05T09:54:14.114661+00:00"}