{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U2IIK45K2TVAPUMJ5PWAJ7BQV4","short_pith_number":"pith:U2IIK45K","canonical_record":{"source":{"id":"2505.12409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-18T13:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"af33207cc2f2697aecfacc062853f0d3648124f5159a06b36ac86a13aac96ef9","abstract_canon_sha256":"d1d89b64ecf2eb99ca25537c44858a17054d65a1cadc8338f202770c3944b8c7"},"schema_version":"1.0"},"canonical_sha256":"a6908573aad4ea07d189ebec04fc30af28fedeea553567e64ab1c5ae1e3006be","source":{"kind":"arxiv","id":"2505.12409","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12409","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12409v1","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12409","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"U2IIK45K2TVA","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"U2IIK45K2TVAPUMJ","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"U2IIK45K","created_at":"2026-07-05T11:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U2IIK45K2TVAPUMJ5PWAJ7BQV4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-18T13:22:11Z","cross_cats_sorted":[],"title_canon_sha256":"af33207cc2f2697aecfacc062853f0d3648124f5159a06b36ac86a13aac96ef9","abstract_canon_sha256":"d1d89b64ecf2eb99ca25537c44858a17054d65a1cadc8338f202770c3944b8c7"},"schema_version":"1.0"},"canonical_sha256":"a6908573aad4ea07d189ebec04fc30af28fedeea553567e64ab1c5ae1e3006be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:03.803442Z","signature_b64":"20Jy2fyLP/1A+szciDFPIlWRP5z1sH1K0zgCeYpf7FWcy5lj7wJn2AdMr7OOAXqMqN3MkBwzlN1XtbKH3qWNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6908573aad4ea07d189ebec04fc30af28fedeea553567e64ab1c5ae1e3006be","last_reissued_at":"2026-07-05T11:05:03.802892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:03.802892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12409","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":"2026-07-05T11:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/WHELo2emezt13me2ECWSHKz2HunSt+4yrh6TI/8kLarthHoMF0XwzW+EGBrWB22XJwxcuq4Jk0j0gd/HtSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:27:00.774092Z"},"content_sha256":"08503afe66a25746d7fc59c769c3b0c3f00a82e6475716d774920b466e5acc53","schema_version":"1.0","event_id":"sha256:08503afe66a25746d7fc59c769c3b0c3f00a82e6475716d774920b466e5acc53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U2IIK45K2TVAPUMJ5PWAJ7BQV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Stochastic Multi-Proximal Method for Nonsmooth Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Elnur Gasanov, Laurent Condat, Peter Richt\\'arik","submitted_at":"2025-05-18T13:22:11Z","abstract_excerpt":"Stochastic gradient descent type methods are ubiquitous in machine learning, but they are only applicable to the optimization of differentiable functions. Proximal algorithms are more general and applicable to nonsmooth functions. We propose a new stochastic and variance-reduced algorithm, the Stochastic Multi-Proximal Method (SMPM), in which the proximity operators of a (possibly empty) random subset of functions are called at every iteration, according to an arbitrary sampling distribution. Several existing algorithms, including Point-SAGA (2016), Proxskip (2022) and RandProx-Minibatch (2023"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12409","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/2505.12409/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":"2026-07-05T11:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gt7T4OaCdzRd/VEHzPkLUulfQXr9opl2e6lGU5DUnl0aQAP8Py/yBsAGXh7GPrVqY+JEAhwLNtCj4bEMj1zMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:27:00.774593Z"},"content_sha256":"55f380c5ff0283a21170099f108c2aed26151784b1d49c9ebf75c8b74229967f","schema_version":"1.0","event_id":"sha256:55f380c5ff0283a21170099f108c2aed26151784b1d49c9ebf75c8b74229967f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/bundle.json","state_url":"https://pith.science/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/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":"2026-08-04T22:27:00Z","links":{"resolver":"https://pith.science/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4","bundle":"https://pith.science/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/bundle.json","state":"https://pith.science/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2IIK45K2TVAPUMJ5PWAJ7BQV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U2IIK45K2TVAPUMJ5PWAJ7BQV4","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":"d1d89b64ecf2eb99ca25537c44858a17054d65a1cadc8338f202770c3944b8c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-18T13:22:11Z","title_canon_sha256":"af33207cc2f2697aecfacc062853f0d3648124f5159a06b36ac86a13aac96ef9"},"schema_version":"1.0","source":{"id":"2505.12409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12409","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12409v1","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12409","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"U2IIK45K2TVA","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"U2IIK45K2TVAPUMJ","created_at":"2026-07-05T11:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"U2IIK45K","created_at":"2026-07-05T11:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:55f380c5ff0283a21170099f108c2aed26151784b1d49c9ebf75c8b74229967f","target":"graph","created_at":"2026-07-05T11:05:03Z","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/2505.12409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient descent type methods are ubiquitous in machine learning, but they are only applicable to the optimization of differentiable functions. Proximal algorithms are more general and applicable to nonsmooth functions. We propose a new stochastic and variance-reduced algorithm, the Stochastic Multi-Proximal Method (SMPM), in which the proximity operators of a (possibly empty) random subset of functions are called at every iteration, according to an arbitrary sampling distribution. Several existing algorithms, including Point-SAGA (2016), Proxskip (2022) and RandProx-Minibatch (2023","authors_text":"Elnur Gasanov, Laurent Condat, Peter Richt\\'arik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-18T13:22:11Z","title":"The Stochastic Multi-Proximal Method for Nonsmooth Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12409","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":"sha256:08503afe66a25746d7fc59c769c3b0c3f00a82e6475716d774920b466e5acc53","target":"record","created_at":"2026-07-05T11:05:03Z","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":"d1d89b64ecf2eb99ca25537c44858a17054d65a1cadc8338f202770c3944b8c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-18T13:22:11Z","title_canon_sha256":"af33207cc2f2697aecfacc062853f0d3648124f5159a06b36ac86a13aac96ef9"},"schema_version":"1.0","source":{"id":"2505.12409","kind":"arxiv","version":1}},"canonical_sha256":"a6908573aad4ea07d189ebec04fc30af28fedeea553567e64ab1c5ae1e3006be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6908573aad4ea07d189ebec04fc30af28fedeea553567e64ab1c5ae1e3006be","first_computed_at":"2026-07-05T11:05:03.802892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:03.802892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20Jy2fyLP/1A+szciDFPIlWRP5z1sH1K0zgCeYpf7FWcy5lj7wJn2AdMr7OOAXqMqN3MkBwzlN1XtbKH3qWNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:03.803442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08503afe66a25746d7fc59c769c3b0c3f00a82e6475716d774920b466e5acc53","sha256:55f380c5ff0283a21170099f108c2aed26151784b1d49c9ebf75c8b74229967f"],"state_sha256":"ff8f129803bf6c484c284735a1ffd728d34435d648a74a423011740953dfdb1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vpI6A0Hj3K/0utO9r0+3KvDoXH1bpPk6L6GMV2yGehubXbTsDlTOO+aAKx//SLJO6FVdb/v3x3rHt1u7ryd0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:27:00.777881Z","bundle_sha256":"6d82346d53153223f43f2a67a525186d755ef2b05af4f7678c56df652f6e891c"}}