{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2UZ2CTX6ISWSA7NXJUIYZARWOP","short_pith_number":"pith:2UZ2CTX6","schema_version":"1.0","canonical_sha256":"d533a14efe44ad207db74d118c823673db8bbb543d6f5e6faa3e42c6c40a6796","source":{"kind":"arxiv","id":"2310.11862","version":3},"attestation_state":"computed","paper":{"title":"Learning to Generate Parameters of ConvNets for Unseen Image Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Li, Guoren Wang, Kaituo Feng, Shiye Wang, Ye Yuan","submitted_at":"2023-10-18T10:26:18Z","abstract_excerpt":"Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive. In this paper, we propose a new training paradigm and formulate the parameter learning of ConvNets into a prediction task: given a ConvNet architecture, we observe there exist correlations between image datasets and their corresponding optimal network parameters, and explore if we can learn a hyper-mapping between them to capture the relations, suc"},"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":"2310.11862","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T10:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"e549bb35b1df88d12d4370b10bdf464f142de99a76129dc0251539ce24e88ef0","abstract_canon_sha256":"be84641889a576ef1a30e88816036ce205e9452245a00b9a35b3e7160530fd24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:52.154948Z","signature_b64":"oR/bRWWwzE0gyl3bmQVbSrncr7kVC/xVRcTijBb2vaNWpuGFm8a7sliZ6DWZYpgIc6SShLIgKzqnfSZjEvvDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d533a14efe44ad207db74d118c823673db8bbb543d6f5e6faa3e42c6c40a6796","last_reissued_at":"2026-07-05T08:53:52.154516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:52.154516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Generate Parameters of ConvNets for Unseen Image Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Li, Guoren Wang, Kaituo Feng, Shiye Wang, Ye Yuan","submitted_at":"2023-10-18T10:26:18Z","abstract_excerpt":"Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive. In this paper, we propose a new training paradigm and formulate the parameter learning of ConvNets into a prediction task: given a ConvNet architecture, we observe there exist correlations between image datasets and their corresponding optimal network parameters, and explore if we can learn a hyper-mapping between them to capture the relations, suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11862","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/2310.11862/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":"2310.11862","created_at":"2026-07-05T08:53:52.154573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11862v3","created_at":"2026-07-05T08:53:52.154573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11862","created_at":"2026-07-05T08:53:52.154573+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UZ2CTX6ISWS","created_at":"2026-07-05T08:53:52.154573+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UZ2CTX6ISWSA7NX","created_at":"2026-07-05T08:53:52.154573+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UZ2CTX6","created_at":"2026-07-05T08:53:52.154573+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/2UZ2CTX6ISWSA7NXJUIYZARWOP","json":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP.json","graph_json":"https://pith.science/api/pith-number/2UZ2CTX6ISWSA7NXJUIYZARWOP/graph.json","events_json":"https://pith.science/api/pith-number/2UZ2CTX6ISWSA7NXJUIYZARWOP/events.json","paper":"https://pith.science/paper/2UZ2CTX6"},"agent_actions":{"view_html":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP","download_json":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP.json","view_paper":"https://pith.science/paper/2UZ2CTX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11862&json=true","fetch_graph":"https://pith.science/api/pith-number/2UZ2CTX6ISWSA7NXJUIYZARWOP/graph.json","fetch_events":"https://pith.science/api/pith-number/2UZ2CTX6ISWSA7NXJUIYZARWOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP/action/storage_attestation","attest_author":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP/action/author_attestation","sign_citation":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP/action/citation_signature","submit_replication":"https://pith.science/pith/2UZ2CTX6ISWSA7NXJUIYZARWOP/action/replication_record"}},"created_at":"2026-07-05T08:53:52.154573+00:00","updated_at":"2026-07-05T08:53:52.154573+00:00"}