{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AKH36ATNV6VVYB2AJ44SCYLMLJ","short_pith_number":"pith:AKH36ATN","canonical_record":{"source":{"id":"2004.10802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-22T19:16:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cff65125676e57bf3c5f47cabaecfd8e7cf0961e60ab2cf5a9356ac803a6d750","abstract_canon_sha256":"76f701cb8eb63019b79081941f62ee4dd0856fdbcdf1bb6666f98ca6f817fc09"},"schema_version":"1.0"},"canonical_sha256":"028fbf026dafab5c07404f3921616c5a62e9286d8821599fff984b7b8e2f223e","source":{"kind":"arxiv","id":"2004.10802","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.10802","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.10802v1","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10802","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKH36ATNV6VV","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKH36ATNV6VVYB2A","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKH36ATN","created_at":"2026-07-05T00:57:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AKH36ATNV6VVYB2AJ44SCYLMLJ","target":"record","payload":{"canonical_record":{"source":{"id":"2004.10802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-22T19:16:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cff65125676e57bf3c5f47cabaecfd8e7cf0961e60ab2cf5a9356ac803a6d750","abstract_canon_sha256":"76f701cb8eb63019b79081941f62ee4dd0856fdbcdf1bb6666f98ca6f817fc09"},"schema_version":"1.0"},"canonical_sha256":"028fbf026dafab5c07404f3921616c5a62e9286d8821599fff984b7b8e2f223e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:36.339492Z","signature_b64":"b1yF9VWYPCChx4UQ8WhcJbken/A1KccPwN1p87gciuZ6aRqDCsnArfla27tMYUlj8mlIWq8RtqFoGUIeeLStAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"028fbf026dafab5c07404f3921616c5a62e9286d8821599fff984b7b8e2f223e","last_reissued_at":"2026-07-05T00:57:36.339046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:36.339046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.10802","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":"2026-07-05T00:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdZuEjM/BIY4IxkxbQSDCRvPjW9bvcQV5yW9b4BPUd82P6Kx/RfEagsaRZfxTnfji6xWNtnPuOEb1KHqaQPIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:23:11.795244Z"},"content_sha256":"84f20eaad97438fcb849e371561569bc4c6c49fb8f1830e112ee0826f3a8d57f","schema_version":"1.0","event_id":"sha256:84f20eaad97438fcb849e371561569bc4c6c49fb8f1830e112ee0826f3a8d57f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AKH36ATNV6VVYB2AJ44SCYLMLJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Neural Scaling Law from the Dimension of the Data Manifold","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jared Kaplan, Utkarsh Sharma","submitted_at":"2020-04-22T19:16:06Z","abstract_excerpt":"When data is plentiful, the loss achieved by well-trained neural networks scales as a power-law $L \\propto N^{-\\alpha}$ in the number of network parameters $N$. This empirical scaling law holds for a wide variety of data modalities, and may persist over many orders of magnitude. The scaling law can be explained if neural models are effectively just performing regression on a data manifold of intrinsic dimension $d$. This simple theory predicts that the scaling exponents $\\alpha \\approx 4/d$ for cross-entropy and mean-squared error losses. We confirm the theory by independently measuring the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10802","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.10802/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":"2026-07-05T00:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8eY1xFRJzEL9C+NCuyfmhXOtfUwJkOM6hK6CKl2Vz/fCY+HhGT3QGehda8Fyye0LzCSEQetuPp81m5G4fPKCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:23:11.796638Z"},"content_sha256":"7c0ad9aed14a56fcef0386f9469013c2a88a4793e539076e8a67fcf510566ff7","schema_version":"1.0","event_id":"sha256:7c0ad9aed14a56fcef0386f9469013c2a88a4793e539076e8a67fcf510566ff7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/bundle.json","state_url":"https://pith.science/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/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":"2026-08-11T12:23:11Z","links":{"resolver":"https://pith.science/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ","bundle":"https://pith.science/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/bundle.json","state":"https://pith.science/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKH36ATNV6VVYB2AJ44SCYLMLJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AKH36ATNV6VVYB2AJ44SCYLMLJ","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":"76f701cb8eb63019b79081941f62ee4dd0856fdbcdf1bb6666f98ca6f817fc09","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-22T19:16:06Z","title_canon_sha256":"cff65125676e57bf3c5f47cabaecfd8e7cf0961e60ab2cf5a9356ac803a6d750"},"schema_version":"1.0","source":{"id":"2004.10802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.10802","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2004.10802v1","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10802","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKH36ATNV6VV","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKH36ATNV6VVYB2A","created_at":"2026-07-05T00:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKH36ATN","created_at":"2026-07-05T00:57:36Z"}],"graph_snapshots":[{"event_id":"sha256:7c0ad9aed14a56fcef0386f9469013c2a88a4793e539076e8a67fcf510566ff7","target":"graph","created_at":"2026-07-05T00:57:36Z","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/2004.10802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When data is plentiful, the loss achieved by well-trained neural networks scales as a power-law $L \\propto N^{-\\alpha}$ in the number of network parameters $N$. This empirical scaling law holds for a wide variety of data modalities, and may persist over many orders of magnitude. The scaling law can be explained if neural models are effectively just performing regression on a data manifold of intrinsic dimension $d$. This simple theory predicts that the scaling exponents $\\alpha \\approx 4/d$ for cross-entropy and mean-squared error losses. We confirm the theory by independently measuring the in","authors_text":"Jared Kaplan, Utkarsh Sharma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-22T19:16:06Z","title":"A Neural Scaling Law from the Dimension of the Data Manifold"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10802","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":"sha256:84f20eaad97438fcb849e371561569bc4c6c49fb8f1830e112ee0826f3a8d57f","target":"record","created_at":"2026-07-05T00:57:36Z","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":"76f701cb8eb63019b79081941f62ee4dd0856fdbcdf1bb6666f98ca6f817fc09","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-22T19:16:06Z","title_canon_sha256":"cff65125676e57bf3c5f47cabaecfd8e7cf0961e60ab2cf5a9356ac803a6d750"},"schema_version":"1.0","source":{"id":"2004.10802","kind":"arxiv","version":1}},"canonical_sha256":"028fbf026dafab5c07404f3921616c5a62e9286d8821599fff984b7b8e2f223e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"028fbf026dafab5c07404f3921616c5a62e9286d8821599fff984b7b8e2f223e","first_computed_at":"2026-07-05T00:57:36.339046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:57:36.339046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b1yF9VWYPCChx4UQ8WhcJbken/A1KccPwN1p87gciuZ6aRqDCsnArfla27tMYUlj8mlIWq8RtqFoGUIeeLStAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:57:36.339492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.10802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84f20eaad97438fcb849e371561569bc4c6c49fb8f1830e112ee0826f3a8d57f","sha256:7c0ad9aed14a56fcef0386f9469013c2a88a4793e539076e8a67fcf510566ff7"],"state_sha256":"2c6bea55e0250000cca45c4405956ea8384889a3c5206bb51f53120f95639a2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XpLOa4FycuvxYLvXu9Nm9aE6zT9QNia6siPvfL8Q00wC2+IX8VvlQOhf5geJMxkmcxaBrkTu0+qU38LZS7FCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:23:11.803986Z","bundle_sha256":"01ad0339b934f1642245f62aef4bdeafea53dff06a84aa01e216164cab48a7d0"}}