{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LPCGO4WLPPLTHY7SPCCOTLR56B","short_pith_number":"pith:LPCGO4WL","canonical_record":{"source":{"id":"2110.08890","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T18:48:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e31a7b4dcdf11d8cc60803be8acdb00e3b1277d434a151877043bc3d441138cb","abstract_canon_sha256":"88dd2b6a5216919764dc82d230dde6df56680859c5863f824da0e04c3a633a33"},"schema_version":"1.0"},"canonical_sha256":"5bc46772cb7bd733e3f27884e9ae3df06f8acc4ae3b9784ad882d6015e6b1c0b","source":{"kind":"arxiv","id":"2110.08890","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08890","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08890v2","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08890","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"LPCGO4WLPPLT","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"LPCGO4WLPPLTHY7S","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"LPCGO4WL","created_at":"2026-07-05T04:17:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LPCGO4WLPPLTHY7SPCCOTLR56B","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08890","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T18:48:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e31a7b4dcdf11d8cc60803be8acdb00e3b1277d434a151877043bc3d441138cb","abstract_canon_sha256":"88dd2b6a5216919764dc82d230dde6df56680859c5863f824da0e04c3a633a33"},"schema_version":"1.0"},"canonical_sha256":"5bc46772cb7bd733e3f27884e9ae3df06f8acc4ae3b9784ad882d6015e6b1c0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:17.711697Z","signature_b64":"kTSqj38x0B/agugg15913Mz6NsedfKns7qufBddgzM8MT/ckcliKqPXt1weo2AIaiVADihGLQBJ3dCcJGQ0kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc46772cb7bd733e3f27884e9ae3df06f8acc4ae3b9784ad882d6015e6b1c0b","last_reissued_at":"2026-07-05T04:17:17.711087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:17.711087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08890","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8da2fhBSW6P0TKAm+s7Hk2bYUtr0+ce6aF5nPS+qhaVK+FKcl1D/VG5JIlPZgNU6Y5XkOqPV7psiZLdQKadBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:14:24.449417Z"},"content_sha256":"bc53ad1d3121ec7ac6a71c25b42c0a01e23fff6bf01922b1cacc831b75c0d1e1","schema_version":"1.0","event_id":"sha256:bc53ad1d3121ec7ac6a71c25b42c0a01e23fff6bf01922b1cacc831b75c0d1e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LPCGO4WLPPLTHY7SPCCOTLR56B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Network Augmentation for Tiny Deep Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Han Cai, Ji Lin, Song Han","submitted_at":"2021-10-17T18:48:41Z","abstract_excerpt":"We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation, dropout) have shown much success on large neural networks by adding noise to overcome over-fitting. However, we found these techniques hurt the performance of tiny neural networks. We argue that training tiny models are different from large models: rather than augmenting the data, we should augment the model, since tiny models tend to suffer from under-fitting rather than over-fitting due to limited capacity. To al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08890","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/2110.08890/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRIrXVJyrKHIZjKoy1PZtQdBLaKxlgdW8C5LlA0Es5rAkmwEsUK8pBbdX2fkwwYlgHmZgKxvvyQA7dbRBKkgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:14:24.449799Z"},"content_sha256":"7c5b27597d8bf0810f5a27222453ac4ade3700d2e7463c3976133c23b0b49419","schema_version":"1.0","event_id":"sha256:7c5b27597d8bf0810f5a27222453ac4ade3700d2e7463c3976133c23b0b49419"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/bundle.json","state_url":"https://pith.science/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:14:24Z","links":{"resolver":"https://pith.science/pith/LPCGO4WLPPLTHY7SPCCOTLR56B","bundle":"https://pith.science/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/bundle.json","state":"https://pith.science/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPCGO4WLPPLTHY7SPCCOTLR56B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LPCGO4WLPPLTHY7SPCCOTLR56B","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":"88dd2b6a5216919764dc82d230dde6df56680859c5863f824da0e04c3a633a33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T18:48:41Z","title_canon_sha256":"e31a7b4dcdf11d8cc60803be8acdb00e3b1277d434a151877043bc3d441138cb"},"schema_version":"1.0","source":{"id":"2110.08890","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08890","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08890v2","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08890","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"LPCGO4WLPPLT","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"LPCGO4WLPPLTHY7S","created_at":"2026-07-05T04:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"LPCGO4WL","created_at":"2026-07-05T04:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:7c5b27597d8bf0810f5a27222453ac4ade3700d2e7463c3976133c23b0b49419","target":"graph","created_at":"2026-07-05T04:17:17Z","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/2110.08890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation, dropout) have shown much success on large neural networks by adding noise to overcome over-fitting. However, we found these techniques hurt the performance of tiny neural networks. We argue that training tiny models are different from large models: rather than augmenting the data, we should augment the model, since tiny models tend to suffer from under-fitting rather than over-fitting due to limited capacity. To al","authors_text":"Chuang Gan, Han Cai, Ji Lin, Song Han","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T18:48:41Z","title":"Network Augmentation for Tiny Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08890","kind":"arxiv","version":2},"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:bc53ad1d3121ec7ac6a71c25b42c0a01e23fff6bf01922b1cacc831b75c0d1e1","target":"record","created_at":"2026-07-05T04:17:17Z","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":"88dd2b6a5216919764dc82d230dde6df56680859c5863f824da0e04c3a633a33","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T18:48:41Z","title_canon_sha256":"e31a7b4dcdf11d8cc60803be8acdb00e3b1277d434a151877043bc3d441138cb"},"schema_version":"1.0","source":{"id":"2110.08890","kind":"arxiv","version":2}},"canonical_sha256":"5bc46772cb7bd733e3f27884e9ae3df06f8acc4ae3b9784ad882d6015e6b1c0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bc46772cb7bd733e3f27884e9ae3df06f8acc4ae3b9784ad882d6015e6b1c0b","first_computed_at":"2026-07-05T04:17:17.711087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:17.711087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kTSqj38x0B/agugg15913Mz6NsedfKns7qufBddgzM8MT/ckcliKqPXt1weo2AIaiVADihGLQBJ3dCcJGQ0kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:17.711697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08890","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc53ad1d3121ec7ac6a71c25b42c0a01e23fff6bf01922b1cacc831b75c0d1e1","sha256:7c5b27597d8bf0810f5a27222453ac4ade3700d2e7463c3976133c23b0b49419"],"state_sha256":"30e92ccab727d8e76b36f60bdc1fcd49bd13a56665f15f596fb9c3bc3237895b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQbCqxTrDddFC4DMyjgAjWwVZxc5C4i2bxBZNK3sQRFupBD8sQW90X0E9ggywYYSh+kIXWlbG+dVKwTrhTdfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:14:24.452215Z","bundle_sha256":"9c87ae6a6081754ec5fd73b0f7a7fa5ad5f0b962e4bfb4b267ec23b18f630889"}}