{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EL653LBXCD642CSN3ZSUSUSAUA","short_pith_number":"pith:EL653LBX","canonical_record":{"source":{"id":"2307.15775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-28T19:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"08ef42a052e3b6e5c780772975e2487087dcc9b908d27636cda71500d1dad672","abstract_canon_sha256":"ca398f8c6ac4c7fdbca5829dcf5b2eaf8b69fa6fd59e754dbefda6ca9188a77a"},"schema_version":"1.0"},"canonical_sha256":"22fdddac3710fdcd0a4dde65495240a02ccd2759afaf70f228ab785d5025af60","source":{"kind":"arxiv","id":"2307.15775","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15775","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15775v2","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15775","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"EL653LBXCD64","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"EL653LBXCD642CSN","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"EL653LBX","created_at":"2026-07-05T08:21:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EL653LBXCD642CSN3ZSUSUSAUA","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-28T19:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"08ef42a052e3b6e5c780772975e2487087dcc9b908d27636cda71500d1dad672","abstract_canon_sha256":"ca398f8c6ac4c7fdbca5829dcf5b2eaf8b69fa6fd59e754dbefda6ca9188a77a"},"schema_version":"1.0"},"canonical_sha256":"22fdddac3710fdcd0a4dde65495240a02ccd2759afaf70f228ab785d5025af60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:40.184556Z","signature_b64":"0ElBF6poQDQyCW37T0vXVBySxvuyfK3Cwwjz/tGbtSQW08BQTxDPc1ZAM3TZYnuFKsh7BQOLJMphoexCnEvgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22fdddac3710fdcd0a4dde65495240a02ccd2759afaf70f228ab785d5025af60","last_reissued_at":"2026-07-05T08:21:40.184095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:40.184095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15775","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMxv2Ggl2wkFIULJuj27/Mboy3nZLKlOBx7mPItK4VFNx/mfayCtHv7HgidTOvKEqr/5OE4fwoy9Tr/qYtd9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:54:57.113283Z"},"content_sha256":"6dad3a73a54990ad2457e4927e3de3d27a8baef2838e042c9f626c2e3c5e13d8","schema_version":"1.0","event_id":"sha256:6dad3a73a54990ad2457e4927e3de3d27a8baef2838e042c9f626c2e3c5e13d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EL653LBXCD642CSN3ZSUSUSAUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CMA Light: a novel Minibatch Algorithm for large-scale non convex finite sum optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Corrado Coppola, Giampaolo Liuzzi, Laura Palagi","submitted_at":"2023-07-28T19:30:04Z","abstract_excerpt":"The supervised training of a deep neural network on a given dataset consists in the unconstrained minimization of the finite sum of continuously differentiable functions, commonly referred to as loss with respect to the samples. These functions depend on the network parameters and most of the times are non-convex. We develop CMA Light, a globally convergent mini-batch gradient method to tackle this problem. We consider the recently introduced Controlled Minibatch Algorithm (CMA) framework and we overcome its main bottleneck, removing the need for at least one evaluation of the whole objective "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15775","kind":"arxiv","version":2},"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/2307.15775/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":"2026-07-05T08:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/Z1os2wL7ce8lGLEKfslq4n3d3eOWjvILqrerlfI4khfMNaDxXPjJw5Bi45YN+cNeAlrA6EqBUrAhIfxDhZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:54:57.113829Z"},"content_sha256":"5a81a749ba7dfa282005af2c81f30943ceb9f3643c5b8c34bfbe844bd8a9a4e5","schema_version":"1.0","event_id":"sha256:5a81a749ba7dfa282005af2c81f30943ceb9f3643c5b8c34bfbe844bd8a9a4e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EL653LBXCD642CSN3ZSUSUSAUA/bundle.json","state_url":"https://pith.science/pith/EL653LBXCD642CSN3ZSUSUSAUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EL653LBXCD642CSN3ZSUSUSAUA/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":"2026-08-13T15:54:57Z","links":{"resolver":"https://pith.science/pith/EL653LBXCD642CSN3ZSUSUSAUA","bundle":"https://pith.science/pith/EL653LBXCD642CSN3ZSUSUSAUA/bundle.json","state":"https://pith.science/pith/EL653LBXCD642CSN3ZSUSUSAUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EL653LBXCD642CSN3ZSUSUSAUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EL653LBXCD642CSN3ZSUSUSAUA","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":"ca398f8c6ac4c7fdbca5829dcf5b2eaf8b69fa6fd59e754dbefda6ca9188a77a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-28T19:30:04Z","title_canon_sha256":"08ef42a052e3b6e5c780772975e2487087dcc9b908d27636cda71500d1dad672"},"schema_version":"1.0","source":{"id":"2307.15775","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15775","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15775v2","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15775","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"EL653LBXCD64","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"EL653LBXCD642CSN","created_at":"2026-07-05T08:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"EL653LBX","created_at":"2026-07-05T08:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:5a81a749ba7dfa282005af2c81f30943ceb9f3643c5b8c34bfbe844bd8a9a4e5","target":"graph","created_at":"2026-07-05T08:21:40Z","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/2307.15775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The supervised training of a deep neural network on a given dataset consists in the unconstrained minimization of the finite sum of continuously differentiable functions, commonly referred to as loss with respect to the samples. These functions depend on the network parameters and most of the times are non-convex. We develop CMA Light, a globally convergent mini-batch gradient method to tackle this problem. We consider the recently introduced Controlled Minibatch Algorithm (CMA) framework and we overcome its main bottleneck, removing the need for at least one evaluation of the whole objective ","authors_text":"Corrado Coppola, Giampaolo Liuzzi, Laura Palagi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-28T19:30:04Z","title":"CMA Light: a novel Minibatch Algorithm for large-scale non convex finite sum optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15775","kind":"arxiv","version":2},"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":"sha256:6dad3a73a54990ad2457e4927e3de3d27a8baef2838e042c9f626c2e3c5e13d8","target":"record","created_at":"2026-07-05T08:21:40Z","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":"ca398f8c6ac4c7fdbca5829dcf5b2eaf8b69fa6fd59e754dbefda6ca9188a77a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.OC","submitted_at":"2023-07-28T19:30:04Z","title_canon_sha256":"08ef42a052e3b6e5c780772975e2487087dcc9b908d27636cda71500d1dad672"},"schema_version":"1.0","source":{"id":"2307.15775","kind":"arxiv","version":2}},"canonical_sha256":"22fdddac3710fdcd0a4dde65495240a02ccd2759afaf70f228ab785d5025af60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22fdddac3710fdcd0a4dde65495240a02ccd2759afaf70f228ab785d5025af60","first_computed_at":"2026-07-05T08:21:40.184095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:40.184095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ElBF6poQDQyCW37T0vXVBySxvuyfK3Cwwjz/tGbtSQW08BQTxDPc1ZAM3TZYnuFKsh7BQOLJMphoexCnEvgDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:40.184556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15775","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dad3a73a54990ad2457e4927e3de3d27a8baef2838e042c9f626c2e3c5e13d8","sha256:5a81a749ba7dfa282005af2c81f30943ceb9f3643c5b8c34bfbe844bd8a9a4e5"],"state_sha256":"c09f4706403dc13bf26afb29b30d9ccdb06abe167da5d5b91528b6bc296ca2ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HF72bEaTmmBlZDjCtw1jgc+pkzQiS2k7U5WUWASvX6v8f5NG0UXwbZA+hqMYd7AzSZ/zRWQI7YUa2TgXghDBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:54:57.120813Z","bundle_sha256":"cf80094880939931627795fbfaf05fffc5fac7585a5bf640f35bf856d33d7f31"}}