{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PBVFVINBFIQRKSFPHXCRA3MVMM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"13274761150614464d637243bfa8c95c8c829148afdad59498974d17ee0fd008","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T00:25:34Z","title_canon_sha256":"66f1f82442993579f174c84ac69e6daf0fd85da7fa6e0ecda420fa3c1f8f6510"},"schema_version":"1.0","source":{"id":"2103.05152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05152","created_at":"2026-07-05T02:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05152v1","created_at":"2026-07-05T02:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05152","created_at":"2026-07-05T02:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"PBVFVINBFIQR","created_at":"2026-07-05T02:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"PBVFVINBFIQRKSFP","created_at":"2026-07-05T02:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"PBVFVINB","created_at":"2026-07-05T02:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:ca50ea8f55ac56cb1e01245d27d506968a7ea60c32d27e33fc25226081591919","target":"graph","created_at":"2026-07-05T02:21:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.05152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning relies on the availability of a large corpus of data (labeled or unlabeled). Thus, one challenging unsettled question is: how to train a deep network on a relatively small dataset? To tackle this question, we propose an evolution-inspired training approach to boost performance on relatively small datasets. The knowledge evolution (KE) approach splits a deep network into two hypotheses: the fit-hypothesis and the reset-hypothesis. We iteratively evolve the knowledge inside the fit-hypothesis by perturbing the reset-hypothesis for multiple generations. This approach not only boosts","authors_text":"Abhinav Shrivastava, Ahmed Taha, Larry Davis","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T00:25:34Z","title":"Knowledge Evolution in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05152","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:250b730c81bb9c73f94cd05da6b076b89dc2424c7093c1efb8f537c1910f366b","target":"record","created_at":"2026-07-05T02:21:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"13274761150614464d637243bfa8c95c8c829148afdad59498974d17ee0fd008","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T00:25:34Z","title_canon_sha256":"66f1f82442993579f174c84ac69e6daf0fd85da7fa6e0ecda420fa3c1f8f6510"},"schema_version":"1.0","source":{"id":"2103.05152","kind":"arxiv","version":1}},"canonical_sha256":"786a5aa1a12a211548af3dc5106d9563118f105c36c6662710247de464802110","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"786a5aa1a12a211548af3dc5106d9563118f105c36c6662710247de464802110","first_computed_at":"2026-07-05T02:21:23.053363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:23.053363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1tGKEsoSY2cTIUAYqym89b2zpkjS7Y3NYj6qtQxfskGGHJJS7Laqnm7ZM6X0DEqV3wJb9ymwrJyAj0D2LJWYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:23.053755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.05152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:250b730c81bb9c73f94cd05da6b076b89dc2424c7093c1efb8f537c1910f366b","sha256:ca50ea8f55ac56cb1e01245d27d506968a7ea60c32d27e33fc25226081591919"],"state_sha256":"3909b55086e05df951db99946de641553b8cf165544d8699eb03012d9e248b84"}