{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MSY4OM7NJPNTRI7L2YEHFQHPP4","short_pith_number":"pith:MSY4OM7N","canonical_record":{"source":{"id":"1805.07883","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T03:56:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"afd8c886162d21818680368b762d9d76ab1aac39fce6fda5970c7130d1daccdc","abstract_canon_sha256":"89a95342772af28f4106442ce23fb5d5711deaa080619621a60e9731cd6b7555"},"schema_version":"1.0"},"canonical_sha256":"64b1c733ed4bdb38a3ebd60872c0ef7f3faf7c620ef95fdcb0d7f2fa18d98d6f","source":{"kind":"arxiv","id":"1805.07883","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07883","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07883v3","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07883","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"MSY4OM7NJPNT","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSY4OM7NJPNTRI7L","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSY4OM7N","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MSY4OM7NJPNTRI7L2YEHFQHPP4","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07883","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T03:56:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"afd8c886162d21818680368b762d9d76ab1aac39fce6fda5970c7130d1daccdc","abstract_canon_sha256":"89a95342772af28f4106442ce23fb5d5711deaa080619621a60e9731cd6b7555"},"schema_version":"1.0"},"canonical_sha256":"64b1c733ed4bdb38a3ebd60872c0ef7f3faf7c620ef95fdcb0d7f2fa18d98d6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:56.253993Z","signature_b64":"MljKeLVrYVZhBfNxAUiQiWY6mUaFZD8gImcjYemOp5qVVK/WCS5mvFZWpYjo/O6bq3Q/FHfLyqoYmLaWUpa0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64b1c733ed4bdb38a3ebd60872c0ef7f3faf7c620ef95fdcb0d7f2fa18d98d6f","last_reissued_at":"2026-05-17T23:41:56.253454Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:56.253454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07883","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQxTxnLR3VXNZsytX0hVtdA0hAfhZ6k/k3DZ/mdf1EqwlMAvLlclMf1Jqt7YpZJBxffnWUCr2h5TJ9tZLJApAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:00:20.045094Z"},"content_sha256":"36aa0de79d187bbbf5799e9a9d9040fa9d70740185636266d46ffacf0170a1a1","schema_version":"1.0","event_id":"sha256:36aa0de79d187bbbf5799e9a9d9040fa9d70740185636266d46ffacf0170a1a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MSY4OM7NJPNTRI7L2YEHFQHPP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aarti Singh, Ruslan Salakhutdinov, Simon S. Du, Sivaraman Balakrishnan, Xiyu Zhai, Yining Wang","submitted_at":"2018-05-21T03:56:17Z","abstract_excerpt":"It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact parametric representation than their Fully-Connected Neural Network (FNN) counterparts, and consequently require fewer training examples to accurately estimate their parameters. We initiate the study of rigorously characterizing the sample-complexity of estimating CNNs and RNNs. We show that the sample-complexity to learn CNNs and RNNs scales linearly with their intrinsic dimension and this sample-complexity is much"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07883","kind":"arxiv","version":3},"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":"2026-05-17T23:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgxJMH6yWNNrkGDWU+ClHB5gL80P3m8P21yMDbvrTEeJsinCpiOpxh98xrGXXVkSckLWsfoxenDzeND4hDhjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:00:20.045473Z"},"content_sha256":"dff911608f81cbad0e3333b2439190cce40c1e0c10d5bfecf7d9040fcb4783ae","schema_version":"1.0","event_id":"sha256:dff911608f81cbad0e3333b2439190cce40c1e0c10d5bfecf7d9040fcb4783ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/bundle.json","state_url":"https://pith.science/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/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":"2026-06-02T03:00:20Z","links":{"resolver":"https://pith.science/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4","bundle":"https://pith.science/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/bundle.json","state":"https://pith.science/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSY4OM7NJPNTRI7L2YEHFQHPP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MSY4OM7NJPNTRI7L2YEHFQHPP4","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":"89a95342772af28f4106442ce23fb5d5711deaa080619621a60e9731cd6b7555","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T03:56:17Z","title_canon_sha256":"afd8c886162d21818680368b762d9d76ab1aac39fce6fda5970c7130d1daccdc"},"schema_version":"1.0","source":{"id":"1805.07883","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07883","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07883v3","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07883","created_at":"2026-05-17T23:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"MSY4OM7NJPNT","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSY4OM7NJPNTRI7L","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSY4OM7N","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:dff911608f81cbad0e3333b2439190cce40c1e0c10d5bfecf7d9040fcb4783ae","target":"graph","created_at":"2026-05-17T23:41:56Z","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":"It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact parametric representation than their Fully-Connected Neural Network (FNN) counterparts, and consequently require fewer training examples to accurately estimate their parameters. We initiate the study of rigorously characterizing the sample-complexity of estimating CNNs and RNNs. We show that the sample-complexity to learn CNNs and RNNs scales linearly with their intrinsic dimension and this sample-complexity is much","authors_text":"Aarti Singh, Ruslan Salakhutdinov, Simon S. Du, Sivaraman Balakrishnan, Xiyu Zhai, Yining Wang","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T03:56:17Z","title":"How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07883","kind":"arxiv","version":3},"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":"sha256:36aa0de79d187bbbf5799e9a9d9040fa9d70740185636266d46ffacf0170a1a1","target":"record","created_at":"2026-05-17T23:41:56Z","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":"89a95342772af28f4106442ce23fb5d5711deaa080619621a60e9731cd6b7555","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T03:56:17Z","title_canon_sha256":"afd8c886162d21818680368b762d9d76ab1aac39fce6fda5970c7130d1daccdc"},"schema_version":"1.0","source":{"id":"1805.07883","kind":"arxiv","version":3}},"canonical_sha256":"64b1c733ed4bdb38a3ebd60872c0ef7f3faf7c620ef95fdcb0d7f2fa18d98d6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64b1c733ed4bdb38a3ebd60872c0ef7f3faf7c620ef95fdcb0d7f2fa18d98d6f","first_computed_at":"2026-05-17T23:41:56.253454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:56.253454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MljKeLVrYVZhBfNxAUiQiWY6mUaFZD8gImcjYemOp5qVVK/WCS5mvFZWpYjo/O6bq3Q/FHfLyqoYmLaWUpa0AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:56.253993Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07883","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36aa0de79d187bbbf5799e9a9d9040fa9d70740185636266d46ffacf0170a1a1","sha256:dff911608f81cbad0e3333b2439190cce40c1e0c10d5bfecf7d9040fcb4783ae"],"state_sha256":"ccac28228933e0af60c3e88f39f3a93058e4f161df9d5bb443cb58a62e0ec2c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvM+6zqzLGN7Xywncy5in5NpEbHEt3/4wthmWQqLtH412PoQlaBQUEFll/bCxxvUDG4XwDI5IYD3Zpm7rMMiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T03:00:20.047429Z","bundle_sha256":"3b7160f1defdf12aa583638f7275bfa635c1f10999ad7ce2abf9322e356c11d0"}}