{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SBNBEY4TAGHNMH5KDL3JAZOHEY","short_pith_number":"pith:SBNBEY4T","canonical_record":{"source":{"id":"2412.15745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-20T10:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"3e89b094bccd3891a548c92f7a835dd4c2ac37a498fee1a916728bf2e1adc69f","abstract_canon_sha256":"93befc446054ba6404462b24ee2edde7f85250efcce2d790d3aeb614c1e849a5"},"schema_version":"1.0"},"canonical_sha256":"905a126393018ed61faa1af69065c7261f15a14412746f32a4457184b70e8456","source":{"kind":"arxiv","id":"2412.15745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15745","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15745v1","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15745","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"SBNBEY4TAGHN","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"SBNBEY4TAGHNMH5K","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"SBNBEY4T","created_at":"2026-07-05T09:52:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SBNBEY4TAGHNMH5KDL3JAZOHEY","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-20T10:04:59Z","cross_cats_sorted":[],"title_canon_sha256":"3e89b094bccd3891a548c92f7a835dd4c2ac37a498fee1a916728bf2e1adc69f","abstract_canon_sha256":"93befc446054ba6404462b24ee2edde7f85250efcce2d790d3aeb614c1e849a5"},"schema_version":"1.0"},"canonical_sha256":"905a126393018ed61faa1af69065c7261f15a14412746f32a4457184b70e8456","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:29.348038Z","signature_b64":"6RnHu666ad5M60qIgi+hX5a2w9DqzelT88k+ELfiTddMGHfKIyOaQK41gCvoH1uRpyEzl4L3B5w6Cz71lzsuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"905a126393018ed61faa1af69065c7261f15a14412746f32a4457184b70e8456","last_reissued_at":"2026-07-05T09:52:29.347623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:29.347623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15745","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":"2026-07-05T09:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCOOGBf9Ahct6B/NYAH9Jt0kQPyVHzsW1RBB1/nfzN5AWCCmNZnt8Iz2KQSnDzIe/KWmhw5c5zoAGqQiGH3SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:50:32.522083Z"},"content_sha256":"5714e96ccdcddd5d147b2631aa792919f8c5fe7eb0cc8df6885933747a468ffa","schema_version":"1.0","event_id":"sha256:5714e96ccdcddd5d147b2631aa792919f8c5fe7eb0cc8df6885933747a468ffa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SBNBEY4TAGHNMH5KDL3JAZOHEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Learning Rate Decay for Stochastic Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Gil Robalo Rei, Maximilian Dinkel, Wolfgang A. Wall","submitted_at":"2024-12-20T10:04:59Z","abstract_excerpt":"Like many optimization algorithms, Stochastic Variational Inference (SVI) is sensitive to the choice of the learning rate. If the learning rate is too small, the optimization process may be slow, and the algorithm might get stuck in local optima. On the other hand, if the learning rate is too large, the algorithm may oscillate or diverge, failing to converge to a solution. Adaptive learning rate methods such as Adam, AdaMax, Adagrad, or RMSprop automatically adjust the learning rate based on the history of gradients. Nevertheless, if the base learning rate is too large, the variational paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15745","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/2412.15745/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":"2026-07-05T09:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73hBQDzX9ofcdG31Xmkh9Ll7S8MxBL32MrvoNihIEBMRH07bTTzUaRSs/T0hdxTVK4Gl/MkTyL9ivVzEWLgCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:50:32.522694Z"},"content_sha256":"7ee2b9764484790cfa70c2394196c3872c9167a73df68c9e5059acd2b73a9ed2","schema_version":"1.0","event_id":"sha256:7ee2b9764484790cfa70c2394196c3872c9167a73df68c9e5059acd2b73a9ed2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/bundle.json","state_url":"https://pith.science/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/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":"2026-08-21T15:50:32Z","links":{"resolver":"https://pith.science/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY","bundle":"https://pith.science/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/bundle.json","state":"https://pith.science/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBNBEY4TAGHNMH5KDL3JAZOHEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SBNBEY4TAGHNMH5KDL3JAZOHEY","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":"93befc446054ba6404462b24ee2edde7f85250efcce2d790d3aeb614c1e849a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-20T10:04:59Z","title_canon_sha256":"3e89b094bccd3891a548c92f7a835dd4c2ac37a498fee1a916728bf2e1adc69f"},"schema_version":"1.0","source":{"id":"2412.15745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15745","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15745v1","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15745","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"SBNBEY4TAGHN","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"SBNBEY4TAGHNMH5K","created_at":"2026-07-05T09:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"SBNBEY4T","created_at":"2026-07-05T09:52:29Z"}],"graph_snapshots":[{"event_id":"sha256:7ee2b9764484790cfa70c2394196c3872c9167a73df68c9e5059acd2b73a9ed2","target":"graph","created_at":"2026-07-05T09:52:29Z","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/2412.15745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Like many optimization algorithms, Stochastic Variational Inference (SVI) is sensitive to the choice of the learning rate. If the learning rate is too small, the optimization process may be slow, and the algorithm might get stuck in local optima. On the other hand, if the learning rate is too large, the algorithm may oscillate or diverge, failing to converge to a solution. Adaptive learning rate methods such as Adam, AdaMax, Adagrad, or RMSprop automatically adjust the learning rate based on the history of gradients. Nevertheless, if the base learning rate is too large, the variational paramet","authors_text":"Gil Robalo Rei, Maximilian Dinkel, Wolfgang A. Wall","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-20T10:04:59Z","title":"Dynamic Learning Rate Decay for Stochastic Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15745","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":"sha256:5714e96ccdcddd5d147b2631aa792919f8c5fe7eb0cc8df6885933747a468ffa","target":"record","created_at":"2026-07-05T09:52:29Z","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":"93befc446054ba6404462b24ee2edde7f85250efcce2d790d3aeb614c1e849a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-12-20T10:04:59Z","title_canon_sha256":"3e89b094bccd3891a548c92f7a835dd4c2ac37a498fee1a916728bf2e1adc69f"},"schema_version":"1.0","source":{"id":"2412.15745","kind":"arxiv","version":1}},"canonical_sha256":"905a126393018ed61faa1af69065c7261f15a14412746f32a4457184b70e8456","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"905a126393018ed61faa1af69065c7261f15a14412746f32a4457184b70e8456","first_computed_at":"2026-07-05T09:52:29.347623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:29.347623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RnHu666ad5M60qIgi+hX5a2w9DqzelT88k+ELfiTddMGHfKIyOaQK41gCvoH1uRpyEzl4L3B5w6Cz71lzsuDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:29.348038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5714e96ccdcddd5d147b2631aa792919f8c5fe7eb0cc8df6885933747a468ffa","sha256:7ee2b9764484790cfa70c2394196c3872c9167a73df68c9e5059acd2b73a9ed2"],"state_sha256":"3b2739cb81d988e24917a9c7a24a3c66eec9d10854fa69b526c38e447ac44b3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PeVJIONKRltIOAHV8amB82UDky3nlqFfnKIy1tXX80Zrf6GOwzPAZgFmZuVvVV9+lSDvFG82nxgDSVqhLdY1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:50:32.530177Z","bundle_sha256":"bb2b4eb271000998e4eae5b84d314fc2ec3e265be5840cea0d6747765c037ae0"}}