{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QNJNSCGHAJKQBMOILDQJRPPH5E","short_pith_number":"pith:QNJNSCGH","canonical_record":{"source":{"id":"2304.05187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T12:45:52Z","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"title_canon_sha256":"fc9e289156c57abd4fd4ff35f2053389b9a05030220880a8dc9e17aa5a7b5e53","abstract_canon_sha256":"3839b17cca32c7c2260bfdd729c9a5e5e0f5e222f8d0aebb1528a6692176ce26"},"schema_version":"1.0"},"canonical_sha256":"8352d908c7025500b1c858e098bde7e92213b8d76798201d0cbcf44cb86c6897","source":{"kind":"arxiv","id":"2304.05187","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05187","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05187v1","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05187","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_12","alias_value":"QNJNSCGHAJKQ","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_16","alias_value":"QNJNSCGHAJKQBMOI","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_8","alias_value":"QNJNSCGH","created_at":"2026-07-05T05:59:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QNJNSCGHAJKQBMOILDQJRPPH5E","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T12:45:52Z","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"title_canon_sha256":"fc9e289156c57abd4fd4ff35f2053389b9a05030220880a8dc9e17aa5a7b5e53","abstract_canon_sha256":"3839b17cca32c7c2260bfdd729c9a5e5e0f5e222f8d0aebb1528a6692176ce26"},"schema_version":"1.0"},"canonical_sha256":"8352d908c7025500b1c858e098bde7e92213b8d76798201d0cbcf44cb86c6897","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:56.522250Z","signature_b64":"aMDxMKI2KRjxZVwD0ocOfxZ0EDLfSzPWulmjnSKiZG5cjjZO5XxJNV+3YZOfzleQJXwIZFWMf037H9iQ7kJCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8352d908c7025500b1c858e098bde7e92213b8d76798201d0cbcf44cb86c6897","last_reissued_at":"2026-07-05T05:59:56.521736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:56.521736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05187","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":"2026-07-05T05:59:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0FdJPA99dhVX4p2NiDMHhG9b4jnXcYrsBpzVf7xlx7fqxRNffAAFjcBONDannDnoLUL0/GHDhurFS+SlDg8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:20:39.403149Z"},"content_sha256":"194b839ef018dc25cf42daa03edad90678dc1e2633ddb4cafe8db98f0d7ea5ee","schema_version":"1.0","event_id":"sha256:194b839ef018dc25cf42daa03edad90678dc1e2633ddb4cafe8db98f0d7ea5ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QNJNSCGHAJKQBMOILDQJRPPH5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Gradient Descent: Deep Learning without Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris Mingard, Jeremy Bernstein, Kevin Huang, Navid Azizan, Yisong Yue","submitted_at":"2023-04-11T12:45:52Z","abstract_excerpt":"The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation frameworks neglect this information in favour of implicit architectural information (e.g. second-order methods) or architecture-agnostic distance functions (e.g. mirror descent). Meanwhile, the most popular optimiser in practice, Adam, is based on heuristics. This paper builds a new framework for deriving optimisation algorithms that explicitly leverage neural architecture. The theory extends mirror descent to non-conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05187","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/2304.05187/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":"2026-07-05T05:59:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6jaSc9O/VSCC07Wm4Llsiz4VGGSDzTzMbNadnZHruS+qhcijRYsfzTPv/2HELp2h0uxtSt5/0qN3WVx0JOOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:20:39.403539Z"},"content_sha256":"376d9e986c65502bdd5a8d8f00b470499247d14bf565fac8c7cdaa82d2bec7f0","schema_version":"1.0","event_id":"sha256:376d9e986c65502bdd5a8d8f00b470499247d14bf565fac8c7cdaa82d2bec7f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/bundle.json","state_url":"https://pith.science/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/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":"2026-07-08T02:20:39Z","links":{"resolver":"https://pith.science/pith/QNJNSCGHAJKQBMOILDQJRPPH5E","bundle":"https://pith.science/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/bundle.json","state":"https://pith.science/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNJNSCGHAJKQBMOILDQJRPPH5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QNJNSCGHAJKQBMOILDQJRPPH5E","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":"3839b17cca32c7c2260bfdd729c9a5e5e0f5e222f8d0aebb1528a6692176ce26","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T12:45:52Z","title_canon_sha256":"fc9e289156c57abd4fd4ff35f2053389b9a05030220880a8dc9e17aa5a7b5e53"},"schema_version":"1.0","source":{"id":"2304.05187","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05187","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05187v1","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05187","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_12","alias_value":"QNJNSCGHAJKQ","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_16","alias_value":"QNJNSCGHAJKQBMOI","created_at":"2026-07-05T05:59:56Z"},{"alias_kind":"pith_short_8","alias_value":"QNJNSCGH","created_at":"2026-07-05T05:59:56Z"}],"graph_snapshots":[{"event_id":"sha256:376d9e986c65502bdd5a8d8f00b470499247d14bf565fac8c7cdaa82d2bec7f0","target":"graph","created_at":"2026-07-05T05:59:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.05187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation frameworks neglect this information in favour of implicit architectural information (e.g. second-order methods) or architecture-agnostic distance functions (e.g. mirror descent). Meanwhile, the most popular optimiser in practice, Adam, is based on heuristics. This paper builds a new framework for deriving optimisation algorithms that explicitly leverage neural architecture. The theory extends mirror descent to non-conv","authors_text":"Chris Mingard, Jeremy Bernstein, Kevin Huang, Navid Azizan, Yisong Yue","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T12:45:52Z","title":"Automatic Gradient Descent: Deep Learning without Hyperparameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05187","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":"sha256:194b839ef018dc25cf42daa03edad90678dc1e2633ddb4cafe8db98f0d7ea5ee","target":"record","created_at":"2026-07-05T05:59:56Z","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":"3839b17cca32c7c2260bfdd729c9a5e5e0f5e222f8d0aebb1528a6692176ce26","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T12:45:52Z","title_canon_sha256":"fc9e289156c57abd4fd4ff35f2053389b9a05030220880a8dc9e17aa5a7b5e53"},"schema_version":"1.0","source":{"id":"2304.05187","kind":"arxiv","version":1}},"canonical_sha256":"8352d908c7025500b1c858e098bde7e92213b8d76798201d0cbcf44cb86c6897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8352d908c7025500b1c858e098bde7e92213b8d76798201d0cbcf44cb86c6897","first_computed_at":"2026-07-05T05:59:56.521736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:56.521736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMDxMKI2KRjxZVwD0ocOfxZ0EDLfSzPWulmjnSKiZG5cjjZO5XxJNV+3YZOfzleQJXwIZFWMf037H9iQ7kJCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:56.522250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05187","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194b839ef018dc25cf42daa03edad90678dc1e2633ddb4cafe8db98f0d7ea5ee","sha256:376d9e986c65502bdd5a8d8f00b470499247d14bf565fac8c7cdaa82d2bec7f0"],"state_sha256":"79b0c90102f2a63eee361b705cd4653eddd0331f70e120d2ef885366a3ce590c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BrDr1b7QEYylZD5yU0MwcV0Nz8pNRH7l+XnGihR4bFNMALsuoHYSfhalXygm3PSQI+LfsNHo4uzJoiWOL/3BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T02:20:39.405926Z","bundle_sha256":"a5f4cbc0b0f69374c4e39213d0bbac0af16e8e485987e33fa0351a96d0053e5e"}}