{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BX5RQDHC5ZA6YOY46YHWAAB3HU","short_pith_number":"pith:BX5RQDHC","canonical_record":{"source":{"id":"2505.22085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-28T08:07:34Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"8aefc6e39719ed301b1fdc4cc605d98d21472b549f8a89b134fa8d986be2c356","abstract_canon_sha256":"04e6328aca9a4d0800ed8336f81c9dc6ee5c8b122668c707091fad15d1b4b16c"},"schema_version":"1.0"},"canonical_sha256":"0dfb180ce2ee41ec3b1cf60f60003b3d161edf8dc8650355cb7c35d2a71ada8a","source":{"kind":"arxiv","id":"2505.22085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22085","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22085v1","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22085","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"BX5RQDHC5ZA6","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"BX5RQDHC5ZA6YOY4","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"BX5RQDHC","created_at":"2026-07-05T11:11:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BX5RQDHC5ZA6YOY46YHWAAB3HU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-28T08:07:34Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"8aefc6e39719ed301b1fdc4cc605d98d21472b549f8a89b134fa8d986be2c356","abstract_canon_sha256":"04e6328aca9a4d0800ed8336f81c9dc6ee5c8b122668c707091fad15d1b4b16c"},"schema_version":"1.0"},"canonical_sha256":"0dfb180ce2ee41ec3b1cf60f60003b3d161edf8dc8650355cb7c35d2a71ada8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:09.638788Z","signature_b64":"Y2LcjdV1RjFwB4OQeKghdbpLGJG9gSlksx34O2GRgzrziqUzPPZErQML7tu5SCAP6KWW6hYtEI0MrTC6fEs9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dfb180ce2ee41ec3b1cf60f60003b3d161edf8dc8650355cb7c35d2a71ada8a","last_reissued_at":"2026-07-05T11:11:09.638062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:09.638062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22085","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":"2026-07-05T11:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LtA5hOnBgPWov6Nvh1ybZKTNxlusaB35BzWJXJGg1EtiKVr5y+9VFv7l6sRtztDUnJxNZps4YtLEq1ZFLsxZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:27:44.173746Z"},"content_sha256":"44721afa4b6b4ed706aa6db1d8c095671bd8d100eaa3d8377899aa32e44ccbfa","schema_version":"1.0","event_id":"sha256:44721afa4b6b4ed706aa6db1d8c095671bd8d100eaa3d8377899aa32e44ccbfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BX5RQDHC5ZA6YOY46YHWAAB3HU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Adrian Riekert, Arnulf Jentzen, Julian Kranz","submitted_at":"2025-05-28T08:07:34Z","abstract_excerpt":"Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM optimizer. However, depending on the specific optimization problem under consideration, the type and the parameters for the averaging need to be adjusted to achieve the smallest optimization error. In this work we propose an averaging approach, which we refer to as parallel averaged ADAM (PADAM), in which we compute parallely different averaged variants of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22085","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/2505.22085/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":"2026-07-05T11:11:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTILV0zowPKvO76lh5KB/4q9A6fULvf1RaAKz6k6fXVvf53psblaIsa/o1eivsRb8aHRcAQARZGJsW4TMncQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:27:44.174347Z"},"content_sha256":"51a8ee39cf88c3615f9bb72bc6c222b7fb710a25b37201123d893d40d30dd548","schema_version":"1.0","event_id":"sha256:51a8ee39cf88c3615f9bb72bc6c222b7fb710a25b37201123d893d40d30dd548"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/bundle.json","state_url":"https://pith.science/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/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":"2026-08-10T06:27:44Z","links":{"resolver":"https://pith.science/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU","bundle":"https://pith.science/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/bundle.json","state":"https://pith.science/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BX5RQDHC5ZA6YOY46YHWAAB3HU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BX5RQDHC5ZA6YOY46YHWAAB3HU","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":"04e6328aca9a4d0800ed8336f81c9dc6ee5c8b122668c707091fad15d1b4b16c","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-28T08:07:34Z","title_canon_sha256":"8aefc6e39719ed301b1fdc4cc605d98d21472b549f8a89b134fa8d986be2c356"},"schema_version":"1.0","source":{"id":"2505.22085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22085","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22085v1","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22085","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"BX5RQDHC5ZA6","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"BX5RQDHC5ZA6YOY4","created_at":"2026-07-05T11:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"BX5RQDHC","created_at":"2026-07-05T11:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:51a8ee39cf88c3615f9bb72bc6c222b7fb710a25b37201123d893d40d30dd548","target":"graph","created_at":"2026-07-05T11:11:09Z","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/2505.22085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM optimizer. However, depending on the specific optimization problem under consideration, the type and the parameters for the averaging need to be adjusted to achieve the smallest optimization error. In this work we propose an averaging approach, which we refer to as parallel averaged ADAM (PADAM), in which we compute parallely different averaged variants of ","authors_text":"Adrian Riekert, Arnulf Jentzen, Julian Kranz","cross_cats":["cs.LG","cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-28T08:07:34Z","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22085","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":"sha256:44721afa4b6b4ed706aa6db1d8c095671bd8d100eaa3d8377899aa32e44ccbfa","target":"record","created_at":"2026-07-05T11:11:09Z","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":"04e6328aca9a4d0800ed8336f81c9dc6ee5c8b122668c707091fad15d1b4b16c","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-28T08:07:34Z","title_canon_sha256":"8aefc6e39719ed301b1fdc4cc605d98d21472b549f8a89b134fa8d986be2c356"},"schema_version":"1.0","source":{"id":"2505.22085","kind":"arxiv","version":1}},"canonical_sha256":"0dfb180ce2ee41ec3b1cf60f60003b3d161edf8dc8650355cb7c35d2a71ada8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dfb180ce2ee41ec3b1cf60f60003b3d161edf8dc8650355cb7c35d2a71ada8a","first_computed_at":"2026-07-05T11:11:09.638062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:09.638062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y2LcjdV1RjFwB4OQeKghdbpLGJG9gSlksx34O2GRgzrziqUzPPZErQML7tu5SCAP6KWW6hYtEI0MrTC6fEs9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:09.638788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44721afa4b6b4ed706aa6db1d8c095671bd8d100eaa3d8377899aa32e44ccbfa","sha256:51a8ee39cf88c3615f9bb72bc6c222b7fb710a25b37201123d893d40d30dd548"],"state_sha256":"75351451535e5f37ce538745efee05f9d693250f29bf2142c77adc58fab2022c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R6kJl8YOWJa0ocNQuq8LmcF+l8UDdnnGleajQZTC4xIy1aapd46tIQ0vIgdXH4t/zDskkWBulRTW40fYThvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:27:44.178050Z","bundle_sha256":"88fccf1e40a827a7f1f5f62ac714ff4702fd48e9c3c8fddd8fb7ea56e1ec84b7"}}