{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3NZ3TNO73K4MLOAF724ETPF44Q","short_pith_number":"pith:3NZ3TNO7","schema_version":"1.0","canonical_sha256":"db73b9b5dfdab8c5b805feb849bcbce4387c2ed57673ca7794d2e053ed75ab61","source":{"kind":"arxiv","id":"2103.16634","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Invariance in Training Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengxi Ye, Fedor Zhdanov, Qinggang Zhou, Tristan McKinney, Xiong Zhou, Yanfeng Liu","submitted_at":"2021-03-30T19:18:31Z","abstract_excerpt":"Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. We enforce scale invariance with local statistics in the data to align similar samples at diverse scales. To accelerate convergence, we enforce a GL(n)-invariance property with global statistics extracted from a batch such that the gradient descent solution should remain inva"},"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":"2103.16634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T19:18:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e7bc18f7c568551b9b8a21d51061122416365d2ae638afc734fbbe5f31039990","abstract_canon_sha256":"96afc1e7095f560ecc484ad06cea6eef9839915b85826a0f6be4e718cd225e8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:14.055643Z","signature_b64":"QDr2z8ZLk7rxXjT/vSGSrOtcTsLJozU06UugLWAVNbDOJr0VRbsRrQ/7tb9MsQskjEy0YZL5/g40pjMQGlz1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db73b9b5dfdab8c5b805feb849bcbce4387c2ed57673ca7794d2e053ed75ab61","last_reissued_at":"2026-07-05T03:39:14.055222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:14.055222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Invariance in Training Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengxi Ye, Fedor Zhdanov, Qinggang Zhou, Tristan McKinney, Xiong Zhou, Yanfeng Liu","submitted_at":"2021-03-30T19:18:31Z","abstract_excerpt":"Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. We enforce scale invariance with local statistics in the data to align similar samples at diverse scales. To accelerate convergence, we enforce a GL(n)-invariance property with global statistics extracted from a batch such that the gradient descent solution should remain inva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16634","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.16634/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":"2103.16634","created_at":"2026-07-05T03:39:14.055283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16634v2","created_at":"2026-07-05T03:39:14.055283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16634","created_at":"2026-07-05T03:39:14.055283+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NZ3TNO73K4M","created_at":"2026-07-05T03:39:14.055283+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NZ3TNO73K4MLOAF","created_at":"2026-07-05T03:39:14.055283+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NZ3TNO7","created_at":"2026-07-05T03:39:14.055283+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/3NZ3TNO73K4MLOAF724ETPF44Q","json":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q.json","graph_json":"https://pith.science/api/pith-number/3NZ3TNO73K4MLOAF724ETPF44Q/graph.json","events_json":"https://pith.science/api/pith-number/3NZ3TNO73K4MLOAF724ETPF44Q/events.json","paper":"https://pith.science/paper/3NZ3TNO7"},"agent_actions":{"view_html":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q","download_json":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q.json","view_paper":"https://pith.science/paper/3NZ3TNO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16634&json=true","fetch_graph":"https://pith.science/api/pith-number/3NZ3TNO73K4MLOAF724ETPF44Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3NZ3TNO73K4MLOAF724ETPF44Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q/action/storage_attestation","attest_author":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q/action/author_attestation","sign_citation":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q/action/citation_signature","submit_replication":"https://pith.science/pith/3NZ3TNO73K4MLOAF724ETPF44Q/action/replication_record"}},"created_at":"2026-07-05T03:39:14.055283+00:00","updated_at":"2026-07-05T03:39:14.055283+00:00"}