{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:4LWXKZNWV3CMDE72EVUOPN533R","short_pith_number":"pith:4LWXKZNW","canonical_record":{"source":{"id":"1508.05051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-20T17:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"721b8136cd8b542523e6b3343443d465fcb132cbd09d65a800d786bf4598f317","abstract_canon_sha256":"26af9403c87b1f21ff578f7578be62437ef3f00ceedc2ceda1ee514015a6c0ba"},"schema_version":"1.0"},"canonical_sha256":"e2ed7565b6aec4c193fa2568e7b7bbdc7e15222d4d5fbce0ea6dc0823e5c4d97","source":{"kind":"arxiv","id":"1508.05051","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.05051","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"1508.05051v1","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.05051","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"4LWXKZNWV3CM","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4LWXKZNWV3CMDE72","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4LWXKZNW","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:4LWXKZNWV3CMDE72EVUOPN533R","target":"record","payload":{"canonical_record":{"source":{"id":"1508.05051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-20T17:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"721b8136cd8b542523e6b3343443d465fcb132cbd09d65a800d786bf4598f317","abstract_canon_sha256":"26af9403c87b1f21ff578f7578be62437ef3f00ceedc2ceda1ee514015a6c0ba"},"schema_version":"1.0"},"canonical_sha256":"e2ed7565b6aec4c193fa2568e7b7bbdc7e15222d4d5fbce0ea6dc0823e5c4d97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:59.821465Z","signature_b64":"9rX6HgCI55Cxxl0aBxrxnoG7onpMv2RH1EU3nHPKs+XXW4bAh6lk0cJJFq6LVh2Hs6kfAfk+89VB+TJRBMHBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2ed7565b6aec4c193fa2568e7b7bbdc7e15222d4d5fbce0ea6dc0823e5c4d97","last_reissued_at":"2026-05-18T01:34:59.820643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:59.820643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.05051","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQ71D71jnzQqUjfTVGESatxGHz6kQ0MT8Qori9QrdrgfI7q9PbPZ1wJ5lD+iJ9+UKjGgLeLdocikXVdksIZODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:35:07.623331Z"},"content_sha256":"7ae256bcb6766d98c3256e671fc6a004e0cfddb0265a01dee525755c3add6aee","schema_version":"1.0","event_id":"sha256:7ae256bcb6766d98c3256e671fc6a004e0cfddb0265a01dee525755c3add6aee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:4LWXKZNWV3CMDE72EVUOPN533R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Sizing Neural Networks: With Applications to n-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Chiang, Kenton Murray","submitted_at":"2015-08-20T17:21:50Z","abstract_excerpt":"Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings. In this paper, we address the issue of choosing the correct number of units in hidden layers. We introduce a method for automatically adjusting network size by pruning out hidden units through $\\ell_{\\infty,1}$ and $\\ell_{2,1}$ regularization. We apply this method to language modeling and demonstrate its ability to correctly choose the number of hidden units "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.05051","kind":"arxiv","version":1},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ew803lfkR5THcqSy7EL4wZDwHEY27JzSYA+XuQbLh03wU80j2zLXSfx45K7ATJ8KdYl6GRPu0v9seKfw+dxwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:35:07.623686Z"},"content_sha256":"185b8966bbd97bf6c2bcb88ed5fb43da2bc8c790bbcb683c2d3e8e74158beb2d","schema_version":"1.0","event_id":"sha256:185b8966bbd97bf6c2bcb88ed5fb43da2bc8c790bbcb683c2d3e8e74158beb2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4LWXKZNWV3CMDE72EVUOPN533R/bundle.json","state_url":"https://pith.science/pith/4LWXKZNWV3CMDE72EVUOPN533R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4LWXKZNWV3CMDE72EVUOPN533R/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":"2026-06-01T07:35:07Z","links":{"resolver":"https://pith.science/pith/4LWXKZNWV3CMDE72EVUOPN533R","bundle":"https://pith.science/pith/4LWXKZNWV3CMDE72EVUOPN533R/bundle.json","state":"https://pith.science/pith/4LWXKZNWV3CMDE72EVUOPN533R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4LWXKZNWV3CMDE72EVUOPN533R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:4LWXKZNWV3CMDE72EVUOPN533R","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":"26af9403c87b1f21ff578f7578be62437ef3f00ceedc2ceda1ee514015a6c0ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-20T17:21:50Z","title_canon_sha256":"721b8136cd8b542523e6b3343443d465fcb132cbd09d65a800d786bf4598f317"},"schema_version":"1.0","source":{"id":"1508.05051","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.05051","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"1508.05051v1","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.05051","created_at":"2026-05-18T01:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"4LWXKZNWV3CM","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4LWXKZNWV3CMDE72","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4LWXKZNW","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:185b8966bbd97bf6c2bcb88ed5fb43da2bc8c790bbcb683c2d3e8e74158beb2d","target":"graph","created_at":"2026-05-18T01:34:59Z","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"},"paper":{"abstract_excerpt":"Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings. In this paper, we address the issue of choosing the correct number of units in hidden layers. We introduce a method for automatically adjusting network size by pruning out hidden units through $\\ell_{\\infty,1}$ and $\\ell_{2,1}$ regularization. We apply this method to language modeling and demonstrate its ability to correctly choose the number of hidden units ","authors_text":"David Chiang, Kenton Murray","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-20T17:21:50Z","title":"Auto-Sizing Neural Networks: With Applications to n-gram Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.05051","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":"sha256:7ae256bcb6766d98c3256e671fc6a004e0cfddb0265a01dee525755c3add6aee","target":"record","created_at":"2026-05-18T01:34:59Z","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":"26af9403c87b1f21ff578f7578be62437ef3f00ceedc2ceda1ee514015a6c0ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-20T17:21:50Z","title_canon_sha256":"721b8136cd8b542523e6b3343443d465fcb132cbd09d65a800d786bf4598f317"},"schema_version":"1.0","source":{"id":"1508.05051","kind":"arxiv","version":1}},"canonical_sha256":"e2ed7565b6aec4c193fa2568e7b7bbdc7e15222d4d5fbce0ea6dc0823e5c4d97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2ed7565b6aec4c193fa2568e7b7bbdc7e15222d4d5fbce0ea6dc0823e5c4d97","first_computed_at":"2026-05-18T01:34:59.820643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:59.820643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9rX6HgCI55Cxxl0aBxrxnoG7onpMv2RH1EU3nHPKs+XXW4bAh6lk0cJJFq6LVh2Hs6kfAfk+89VB+TJRBMHBBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:59.821465Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.05051","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ae256bcb6766d98c3256e671fc6a004e0cfddb0265a01dee525755c3add6aee","sha256:185b8966bbd97bf6c2bcb88ed5fb43da2bc8c790bbcb683c2d3e8e74158beb2d"],"state_sha256":"41d5e42c163c4fb65f3c29bca6802eddc4423ef35d4371bce08ebaa3e127f07c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SyT+zpfTuVLmNiHvZ0BOikc1BH2KHwtKF7Pv2sSmzOGF5lq74YkunYWkoJQJJ4ocvbK5YeVwKXrL9OszOK8ECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:35:07.625652Z","bundle_sha256":"b19d2b5c2a9fc6ec2ddedd735254865495307b4027d6031e5d1d395ecf288fab"}}