{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RKVPFNHHWB3ZJR36GWCT42IDDF","short_pith_number":"pith:RKVPFNHH","schema_version":"1.0","canonical_sha256":"8aaaf2b4e7b07794c77e35853e6903197024099a1a7ab63eaaec6974721ac063","source":{"kind":"arxiv","id":"1703.04071","version":4},"attestation_state":"computed","paper":{"title":"A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CV","authors_text":"Chunpeng Wu, Hai Li, Tariq Afzal, Wei Wen, Yiran Chen, Yongmei Zhang","submitted_at":"2017-03-12T05:07:00Z","abstract_excerpt":"Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An emerging question, however, is whether these model compression techniques hurt DNN's learning ability other than classifying images on a single dataset. Our preliminary experiment shows that these compression methods could degrade domain adaptation (DA) ability, though the classification performance is preserved. Therefore, we propose a new compact network ar"},"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":"1703.04071","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-12T05:07:00Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"61565b1aee7c15bce2804ddfa24221526f3101de0c15060da38f3e4897c71107","abstract_canon_sha256":"f8067529b3a3755db7136625dab630873f27c00994b165cc454c72f1f58fc2cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:26.013938Z","signature_b64":"hi4Z9HFzjuyA5v7rTrKcAakjHP41vYUF5PO6LO9isXKGGFLfkMLm/6W/n4fbCXLNCk9oDM+RcE1fqkw3sBPzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aaaf2b4e7b07794c77e35853e6903197024099a1a7ab63eaaec6974721ac063","last_reissued_at":"2026-05-18T00:47:26.013275Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:26.013275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CV","authors_text":"Chunpeng Wu, Hai Li, Tariq Afzal, Wei Wen, Yiran Chen, Yongmei Zhang","submitted_at":"2017-03-12T05:07:00Z","abstract_excerpt":"Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An emerging question, however, is whether these model compression techniques hurt DNN's learning ability other than classifying images on a single dataset. Our preliminary experiment shows that these compression methods could degrade domain adaptation (DA) ability, though the classification performance is preserved. Therefore, we propose a new compact network ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04071","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1703.04071","created_at":"2026-05-18T00:47:26.013393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04071v4","created_at":"2026-05-18T00:47:26.013393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04071","created_at":"2026-05-18T00:47:26.013393+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKVPFNHHWB3Z","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKVPFNHHWB3ZJR36","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKVPFNHH","created_at":"2026-05-18T12:31:39.905425+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/RKVPFNHHWB3ZJR36GWCT42IDDF","json":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF.json","graph_json":"https://pith.science/api/pith-number/RKVPFNHHWB3ZJR36GWCT42IDDF/graph.json","events_json":"https://pith.science/api/pith-number/RKVPFNHHWB3ZJR36GWCT42IDDF/events.json","paper":"https://pith.science/paper/RKVPFNHH"},"agent_actions":{"view_html":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF","download_json":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF.json","view_paper":"https://pith.science/paper/RKVPFNHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04071&json=true","fetch_graph":"https://pith.science/api/pith-number/RKVPFNHHWB3ZJR36GWCT42IDDF/graph.json","fetch_events":"https://pith.science/api/pith-number/RKVPFNHHWB3ZJR36GWCT42IDDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF/action/storage_attestation","attest_author":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF/action/author_attestation","sign_citation":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF/action/citation_signature","submit_replication":"https://pith.science/pith/RKVPFNHHWB3ZJR36GWCT42IDDF/action/replication_record"}},"created_at":"2026-05-18T00:47:26.013393+00:00","updated_at":"2026-05-18T00:47:26.013393+00:00"}