{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WXJZNZCKHE5IMQZM34GAX57UN3","short_pith_number":"pith:WXJZNZCK","canonical_record":{"source":{"id":"2307.06987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"cd4a134b7d14913b1c6b50dc12f599290ee6b5e0d076334558f55a510a447177","abstract_canon_sha256":"90ad9164029f7b00e2326d747adc621e373772f209b996df5c870216dfe9ebf2"},"schema_version":"1.0"},"canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","source":{"kind":"arxiv","id":"2307.06987","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06987","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06987v1","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06987","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_12","alias_value":"WXJZNZCKHE5I","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WXJZNZCKHE5IMQZM","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WXJZNZCK","created_at":"2026-07-05T06:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WXJZNZCKHE5IMQZM34GAX57UN3","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"cd4a134b7d14913b1c6b50dc12f599290ee6b5e0d076334558f55a510a447177","abstract_canon_sha256":"90ad9164029f7b00e2326d747adc621e373772f209b996df5c870216dfe9ebf2"},"schema_version":"1.0"},"canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:48.710965Z","signature_b64":"oMziIz/m9/8Ms+nUwpjDWZR5PWQGj5Le168zlIU4UV61oLQSplS07xQMYhrZmgv9XYFQWplNlj01gmTGygfRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","last_reissued_at":"2026-07-05T06:30:48.710436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:48.710436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06987","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":"2026-07-05T06:30:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IL9Lobe0fipD/MxDmfBK6/vysNMzxg8QYNt1Gq1Xmw+WqAkbQyMkcAtt422P1ZcPMfUOVpOuCPFOciby4hEkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:21:12.165501Z"},"content_sha256":"b3dcb13afb1eb0ef6eec1a8c01cd4e37c909a41c7e064a5ee60689c9184cb386","schema_version":"1.0","event_id":"sha256:b3dcb13afb1eb0ef6eec1a8c01cd4e37c909a41c7e064a5ee60689c9184cb386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WXJZNZCKHE5IMQZM34GAX57UN3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A new non-convex framework to improve asymptotical knowledge on generic stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Audrey Repetti, Emilie Chouzenoux, Jean-Baptiste Fest","submitted_at":"2023-07-13T17:49:49Z","abstract_excerpt":"Stochastic gradient optimization methods are broadly used to minimize non-convex smooth objective functions, for instance when training deep neural networks. However, theoretical guarantees on the asymptotic behaviour of these methods remain scarce. Especially, ensuring almost-sure convergence of the iterates to a stationary point is quite challenging. In this work, we introduce a new Kurdyka-Lojasiewicz theoretical framework to analyze asymptotic behavior of stochastic gradient descent (SGD) schemes when minimizing non-convex smooth objectives. In particular, our framework provides new almost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06987","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/2307.06987/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":"2026-07-05T06:30:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcGLM8px0l443FPv+dL0JGBOR0oJu+fVmVFakvGpFQvjdcalAv8eQa0ex9Tc2grz5+1UTCBlAr/bgIOqQOenBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:21:12.165840Z"},"content_sha256":"f5b7ad6343a0dd7d718e39bb20d65c50b0dbef8dc1be03fec560fb01686813f0","schema_version":"1.0","event_id":"sha256:f5b7ad6343a0dd7d718e39bb20d65c50b0dbef8dc1be03fec560fb01686813f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/bundle.json","state_url":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXJZNZCKHE5IMQZM34GAX57UN3/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":"2026-08-15T00:21:12Z","links":{"resolver":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3","bundle":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/bundle.json","state":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXJZNZCKHE5IMQZM34GAX57UN3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WXJZNZCKHE5IMQZM34GAX57UN3","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":"90ad9164029f7b00e2326d747adc621e373772f209b996df5c870216dfe9ebf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","title_canon_sha256":"cd4a134b7d14913b1c6b50dc12f599290ee6b5e0d076334558f55a510a447177"},"schema_version":"1.0","source":{"id":"2307.06987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06987","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06987v1","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06987","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_12","alias_value":"WXJZNZCKHE5I","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WXJZNZCKHE5IMQZM","created_at":"2026-07-05T06:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WXJZNZCK","created_at":"2026-07-05T06:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:f5b7ad6343a0dd7d718e39bb20d65c50b0dbef8dc1be03fec560fb01686813f0","target":"graph","created_at":"2026-07-05T06:30:48Z","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/2307.06987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient optimization methods are broadly used to minimize non-convex smooth objective functions, for instance when training deep neural networks. However, theoretical guarantees on the asymptotic behaviour of these methods remain scarce. Especially, ensuring almost-sure convergence of the iterates to a stationary point is quite challenging. In this work, we introduce a new Kurdyka-Lojasiewicz theoretical framework to analyze asymptotic behavior of stochastic gradient descent (SGD) schemes when minimizing non-convex smooth objectives. In particular, our framework provides new almost","authors_text":"Audrey Repetti, Emilie Chouzenoux, Jean-Baptiste Fest","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","title":"A new non-convex framework to improve asymptotical knowledge on generic stochastic gradient descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06987","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:b3dcb13afb1eb0ef6eec1a8c01cd4e37c909a41c7e064a5ee60689c9184cb386","target":"record","created_at":"2026-07-05T06:30:48Z","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":"90ad9164029f7b00e2326d747adc621e373772f209b996df5c870216dfe9ebf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","title_canon_sha256":"cd4a134b7d14913b1c6b50dc12f599290ee6b5e0d076334558f55a510a447177"},"schema_version":"1.0","source":{"id":"2307.06987","kind":"arxiv","version":1}},"canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","first_computed_at":"2026-07-05T06:30:48.710436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:48.710436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMziIz/m9/8Ms+nUwpjDWZR5PWQGj5Le168zlIU4UV61oLQSplS07xQMYhrZmgv9XYFQWplNlj01gmTGygfRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:48.710965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3dcb13afb1eb0ef6eec1a8c01cd4e37c909a41c7e064a5ee60689c9184cb386","sha256:f5b7ad6343a0dd7d718e39bb20d65c50b0dbef8dc1be03fec560fb01686813f0"],"state_sha256":"38fd86d689fc900645e9d8bbf511f0d1f5eade25e3bd88179827506df988be5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OreP8Vqu5hgoIhlsJIf7w/x9jrdYUWK8ogmwPKzmvu+vLCRinR9TudtHaZjCRZ9hbQ1QmizM9W5KK9ODxTVADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:21:12.168119Z","bundle_sha256":"124dd353be6989505dce2dd12d0b5b4b5d82fd0cd29be4fdfdb137876828293f"}}