{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FMOMQXDDNQOBUFNBJ6IVPAYIUP","short_pith_number":"pith:FMOMQXDD","schema_version":"1.0","canonical_sha256":"2b1cc85c636c1c1a15a14f91578308a3cfe2c590e781da733bab11aef9b4dbcd","source":{"kind":"arxiv","id":"1905.10698","version":2},"attestation_state":"computed","paper":{"title":"Efficient Neural Task Adaptation by Maximum Entropy Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Behrouz Haji Soleimani, Farshid Varno, Lisa Di Jorio, Marzie Saghayi, Stan Matwin","submitted_at":"2019-05-25T23:37:34Z","abstract_excerpt":"Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high energy random noise. This noise is mainly delivered from a careless replacement of task-specific parameters. We analyze theoretically such knowledge contamination for classification tasks and propose a practical and easy to apply method to trap and minimize the contaminant. In our approach, the entropy of the output estimates gets maximized initially and the firs"},"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":"1905.10698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-25T23:37:34Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"df59ec7af3e0f6674a6bd9adb383d2f8fc1fe9c8e52f7652657a738838e9069c","abstract_canon_sha256":"4c5bbd66b1906cdb50e21380440cd01112e1d2d0e05aa2091550f1bf10ad7925"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:48.808030Z","signature_b64":"UVZnUBSOdo9gTpiw+d0VhR/gSvSF8R6Mo0nLTDDiBgP7oyLtic+MdetHk6m/+DVNOHcAO6TciL7AWwH63T98Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b1cc85c636c1c1a15a14f91578308a3cfe2c590e781da733bab11aef9b4dbcd","last_reissued_at":"2026-05-17T23:40:48.807287Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:48.807287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Neural Task Adaptation by Maximum Entropy Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Behrouz Haji Soleimani, Farshid Varno, Lisa Di Jorio, Marzie Saghayi, Stan Matwin","submitted_at":"2019-05-25T23:37:34Z","abstract_excerpt":"Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high energy random noise. This noise is mainly delivered from a careless replacement of task-specific parameters. We analyze theoretically such knowledge contamination for classification tasks and propose a practical and easy to apply method to trap and minimize the contaminant. In our approach, the entropy of the output estimates gets maximized initially and the firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10698","kind":"arxiv","version":2},"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":"1905.10698","created_at":"2026-05-17T23:40:48.807409+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10698v2","created_at":"2026-05-17T23:40:48.807409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10698","created_at":"2026-05-17T23:40:48.807409+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMOMQXDDNQOB","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMOMQXDDNQOBUFNB","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMOMQXDD","created_at":"2026-05-18T12:33:15.570797+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/FMOMQXDDNQOBUFNBJ6IVPAYIUP","json":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP.json","graph_json":"https://pith.science/api/pith-number/FMOMQXDDNQOBUFNBJ6IVPAYIUP/graph.json","events_json":"https://pith.science/api/pith-number/FMOMQXDDNQOBUFNBJ6IVPAYIUP/events.json","paper":"https://pith.science/paper/FMOMQXDD"},"agent_actions":{"view_html":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP","download_json":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP.json","view_paper":"https://pith.science/paper/FMOMQXDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10698&json=true","fetch_graph":"https://pith.science/api/pith-number/FMOMQXDDNQOBUFNBJ6IVPAYIUP/graph.json","fetch_events":"https://pith.science/api/pith-number/FMOMQXDDNQOBUFNBJ6IVPAYIUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP/action/storage_attestation","attest_author":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP/action/author_attestation","sign_citation":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP/action/citation_signature","submit_replication":"https://pith.science/pith/FMOMQXDDNQOBUFNBJ6IVPAYIUP/action/replication_record"}},"created_at":"2026-05-17T23:40:48.807409+00:00","updated_at":"2026-05-17T23:40:48.807409+00:00"}