{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CFXDDAWFCCKUKMW4DL6UODKOCO","short_pith_number":"pith:CFXDDAWF","schema_version":"1.0","canonical_sha256":"116e3182c510954532dc1afd470d4e1395ce5747cd3f767148c4f25cf284be9a","source":{"kind":"arxiv","id":"2212.07700","version":3},"attestation_state":"computed","paper":{"title":"Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Mattia Garavagno, Antonio Frisoli, Daniele Leonardis","submitted_at":"2022-12-15T10:23:32Z","abstract_excerpt":"The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to train a network from scratch. On the other hand, the training of custom and lighter CNNs requires expertise, in the from-scratch case, and or high-end resources, as in the case of hardware-aware neural architecture search (HW NAS), limiting access to the technology by non-habitual NN developers. For this reason, we present ColabNAS, an affordable HW NAS technique for producing li"},"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":"2212.07700","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T10:23:32Z","cross_cats_sorted":[],"title_canon_sha256":"bdf518e0730d9598a3b5d373131bcd7fc725c6a869cf793ae509943a42fd1a56","abstract_canon_sha256":"d0f226bc3cd93c1ed433f93afa182d13d9c3831c1d02decc32cdf962a6e45461"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:45.091584Z","signature_b64":"lloCmczjQG14dGvLgrvqbOEw59byrHBax+EhZphXizfmEcg7B73N+VOWJwzwBi2+Q1c/OPFRPyWdS4pBNJ9GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116e3182c510954532dc1afd470d4e1395ce5747cd3f767148c4f25cf284be9a","last_reissued_at":"2026-06-19T16:09:45.090741Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:45.090741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Mattia Garavagno, Antonio Frisoli, Daniele Leonardis","submitted_at":"2022-12-15T10:23:32Z","abstract_excerpt":"The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to train a network from scratch. On the other hand, the training of custom and lighter CNNs requires expertise, in the from-scratch case, and or high-end resources, as in the case of hardware-aware neural architecture search (HW NAS), limiting access to the technology by non-habitual NN developers. For this reason, we present ColabNAS, an affordable HW NAS technique for producing li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07700","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/2212.07700/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":"2212.07700","created_at":"2026-06-19T16:09:45.090797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07700v3","created_at":"2026-06-19T16:09:45.090797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07700","created_at":"2026-06-19T16:09:45.090797+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFXDDAWFCCKU","created_at":"2026-06-19T16:09:45.090797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFXDDAWFCCKUKMW4","created_at":"2026-06-19T16:09:45.090797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFXDDAWF","created_at":"2026-06-19T16:09:45.090797+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/CFXDDAWFCCKUKMW4DL6UODKOCO","json":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO.json","graph_json":"https://pith.science/api/pith-number/CFXDDAWFCCKUKMW4DL6UODKOCO/graph.json","events_json":"https://pith.science/api/pith-number/CFXDDAWFCCKUKMW4DL6UODKOCO/events.json","paper":"https://pith.science/paper/CFXDDAWF"},"agent_actions":{"view_html":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO","download_json":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO.json","view_paper":"https://pith.science/paper/CFXDDAWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07700&json=true","fetch_graph":"https://pith.science/api/pith-number/CFXDDAWFCCKUKMW4DL6UODKOCO/graph.json","fetch_events":"https://pith.science/api/pith-number/CFXDDAWFCCKUKMW4DL6UODKOCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO/action/storage_attestation","attest_author":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO/action/author_attestation","sign_citation":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO/action/citation_signature","submit_replication":"https://pith.science/pith/CFXDDAWFCCKUKMW4DL6UODKOCO/action/replication_record"}},"created_at":"2026-06-19T16:09:45.090797+00:00","updated_at":"2026-06-19T16:09:45.090797+00:00"}