{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GTXVVQHL77V547AZ4P2L4YCBWF","short_pith_number":"pith:GTXVVQHL","canonical_record":{"source":{"id":"1703.04757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T22:13:41Z","cross_cats_sorted":["physics.data-an","stat.ML"],"title_canon_sha256":"fbf7cccc8693877f4245cdefef7da7a9276c183b5234aeb3916c4e1356fe7da6","abstract_canon_sha256":"7cbd4d77214a42a1f82658f6ce856574ba6cd44e701c77660844276b6a366151"},"schema_version":"1.0"},"canonical_sha256":"34ef5ac0ebffebde7c19e3f4be6041b140380c974849f872a9fda4dd11724d11","source":{"kind":"arxiv","id":"1703.04757","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04757","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04757v3","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04757","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTXVVQHL77V5","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GTXVVQHL77V547AZ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GTXVVQHL","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GTXVVQHL77V547AZ4P2L4YCBWF","target":"record","payload":{"canonical_record":{"source":{"id":"1703.04757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T22:13:41Z","cross_cats_sorted":["physics.data-an","stat.ML"],"title_canon_sha256":"fbf7cccc8693877f4245cdefef7da7a9276c183b5234aeb3916c4e1356fe7da6","abstract_canon_sha256":"7cbd4d77214a42a1f82658f6ce856574ba6cd44e701c77660844276b6a366151"},"schema_version":"1.0"},"canonical_sha256":"34ef5ac0ebffebde7c19e3f4be6041b140380c974849f872a9fda4dd11724d11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:35.189875Z","signature_b64":"6zDKC7365qi9ocm7vev0n7114jByG5CC84+d8qG0x4j4eTaAdDM0HkQEoIlwURNZdyFyVUxrG1gqmGe5kyJKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ef5ac0ebffebde7c19e3f4be6041b140380c974849f872a9fda4dd11724d11","last_reissued_at":"2026-05-18T00:21:35.189131Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:35.189131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.04757","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":"2026-05-18T00:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCFzY3uJRORYyVBez1tDAhn4wKe8wL3jKvp1dcXexLU1ceug6lh+va5lwElwCMr5f5kRkzAkxMj1CiJoYOODBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:39:47.114513Z"},"content_sha256":"5be7fc816c8805f763ee2f2eae45d19f5f49a34ac5e536bff41ce358513a7fe7","schema_version":"1.0","event_id":"sha256:5be7fc816c8805f763ee2f2eae45d19f5f49a34ac5e536bff41ce358513a7fe7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GTXVVQHL77V547AZ4P2L4YCBWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Separation of time scales and direct computation of weights in deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aggelos Katsaggelos, Neda Rohani, Nima Dehmamy","submitted_at":"2017-03-14T22:13:41Z","abstract_excerpt":"Artificial intelligence is revolutionizing our lives at an ever increasing pace. At the heart of this revolution is the recent advancements in deep neural networks (DNN), learning to perform sophisticated, high-level tasks. However, training DNNs requires massive amounts of data and is very computationally intensive. Gaining analytical understanding of the solutions found by DNNs can help us devise more efficient training algorithms, replacing the commonly used mthod of stochastic gradient descent (SGD). We analyze the dynamics of SGD and show that, indeed, direct computation of the solutions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04757","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":"2026-05-18T00:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kl0yv/kTh8xZJiPbbJzro7z1VWKc7DXKNmgckhq1cmox0jfIqIZFrvwT1hNVfrW7L5iAWRz1HYzFtPOf2E/TAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:39:47.114897Z"},"content_sha256":"addc7479f39eb28e03ea06dcd6b6edf7032c85eec2f10c84361b19e74f2ae211","schema_version":"1.0","event_id":"sha256:addc7479f39eb28e03ea06dcd6b6edf7032c85eec2f10c84361b19e74f2ae211"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTXVVQHL77V547AZ4P2L4YCBWF/bundle.json","state_url":"https://pith.science/pith/GTXVVQHL77V547AZ4P2L4YCBWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTXVVQHL77V547AZ4P2L4YCBWF/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":"2026-05-26T00:39:47Z","links":{"resolver":"https://pith.science/pith/GTXVVQHL77V547AZ4P2L4YCBWF","bundle":"https://pith.science/pith/GTXVVQHL77V547AZ4P2L4YCBWF/bundle.json","state":"https://pith.science/pith/GTXVVQHL77V547AZ4P2L4YCBWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTXVVQHL77V547AZ4P2L4YCBWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GTXVVQHL77V547AZ4P2L4YCBWF","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":"7cbd4d77214a42a1f82658f6ce856574ba6cd44e701c77660844276b6a366151","cross_cats_sorted":["physics.data-an","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T22:13:41Z","title_canon_sha256":"fbf7cccc8693877f4245cdefef7da7a9276c183b5234aeb3916c4e1356fe7da6"},"schema_version":"1.0","source":{"id":"1703.04757","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04757","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04757v3","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04757","created_at":"2026-05-18T00:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTXVVQHL77V5","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GTXVVQHL77V547AZ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GTXVVQHL","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:addc7479f39eb28e03ea06dcd6b6edf7032c85eec2f10c84361b19e74f2ae211","target":"graph","created_at":"2026-05-18T00:21:35Z","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":"Artificial intelligence is revolutionizing our lives at an ever increasing pace. At the heart of this revolution is the recent advancements in deep neural networks (DNN), learning to perform sophisticated, high-level tasks. However, training DNNs requires massive amounts of data and is very computationally intensive. Gaining analytical understanding of the solutions found by DNNs can help us devise more efficient training algorithms, replacing the commonly used mthod of stochastic gradient descent (SGD). We analyze the dynamics of SGD and show that, indeed, direct computation of the solutions ","authors_text":"Aggelos Katsaggelos, Neda Rohani, Nima Dehmamy","cross_cats":["physics.data-an","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T22:13:41Z","title":"Separation of time scales and direct computation of weights in deep neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04757","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":"sha256:5be7fc816c8805f763ee2f2eae45d19f5f49a34ac5e536bff41ce358513a7fe7","target":"record","created_at":"2026-05-18T00:21:35Z","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":"7cbd4d77214a42a1f82658f6ce856574ba6cd44e701c77660844276b6a366151","cross_cats_sorted":["physics.data-an","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-14T22:13:41Z","title_canon_sha256":"fbf7cccc8693877f4245cdefef7da7a9276c183b5234aeb3916c4e1356fe7da6"},"schema_version":"1.0","source":{"id":"1703.04757","kind":"arxiv","version":3}},"canonical_sha256":"34ef5ac0ebffebde7c19e3f4be6041b140380c974849f872a9fda4dd11724d11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34ef5ac0ebffebde7c19e3f4be6041b140380c974849f872a9fda4dd11724d11","first_computed_at":"2026-05-18T00:21:35.189131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:35.189131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6zDKC7365qi9ocm7vev0n7114jByG5CC84+d8qG0x4j4eTaAdDM0HkQEoIlwURNZdyFyVUxrG1gqmGe5kyJKBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:35.189875Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.04757","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5be7fc816c8805f763ee2f2eae45d19f5f49a34ac5e536bff41ce358513a7fe7","sha256:addc7479f39eb28e03ea06dcd6b6edf7032c85eec2f10c84361b19e74f2ae211"],"state_sha256":"e4135210aad3a10fae11729fb638190453fb1b995eb3ff981dd0c35e3184d085"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fywBoPvYZRkcqq36MhtVZeIUX3uPq2tkDKNjlSmFRdHwtFUfP1hK259vsqnmXCO2U3m1OP6ejcYu7R7N3CoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:39:47.118478Z","bundle_sha256":"f239b0607f5bb7588611abf419e475a7ad03cde82b56b2add5fda3ee738d5845"}}