{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SZV7ZARVNHWPSSKC7W6IKWU57S","short_pith_number":"pith:SZV7ZARV","canonical_record":{"source":{"id":"1706.00705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-02T14:45:15Z","cross_cats_sorted":["cond-mat.stat-mech","cs.IT","math.IT"],"title_canon_sha256":"4ab3fa10878a349ed5b2ee2155cde3c348e6e7e206cbd1788e31bd74792012ae","abstract_canon_sha256":"8058ebcbab051d0b672a9270c2b0e4303256c28c697c6b3955ae85719bc0a012"},"schema_version":"1.0"},"canonical_sha256":"966bfc823569ecf94942fdbc855a9dfca0e03db71442945e78e7fce8dbb7b3a3","source":{"kind":"arxiv","id":"1706.00705","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00705","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00705v1","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00705","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"SZV7ZARVNHWP","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SZV7ZARVNHWPSSKC","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SZV7ZARV","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SZV7ZARVNHWPSSKC7W6IKWU57S","target":"record","payload":{"canonical_record":{"source":{"id":"1706.00705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-02T14:45:15Z","cross_cats_sorted":["cond-mat.stat-mech","cs.IT","math.IT"],"title_canon_sha256":"4ab3fa10878a349ed5b2ee2155cde3c348e6e7e206cbd1788e31bd74792012ae","abstract_canon_sha256":"8058ebcbab051d0b672a9270c2b0e4303256c28c697c6b3955ae85719bc0a012"},"schema_version":"1.0"},"canonical_sha256":"966bfc823569ecf94942fdbc855a9dfca0e03db71442945e78e7fce8dbb7b3a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:34.351364Z","signature_b64":"CKb4u19wls9pM1EFG6KGszRnzNI5g98gJhCxMI1PS5BoOOJawQKXkT+WbZQmPxzakCI46NJcVfy1fTr0AoQpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966bfc823569ecf94942fdbc855a9dfca0e03db71442945e78e7fce8dbb7b3a3","last_reissued_at":"2026-05-18T00:25:34.350624Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:34.350624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.00705","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":"2026-05-18T00:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QmT0SM/hx727cwGzlFE1ZR1OxJ1trkfkMOfC1EZiWD6GZ4LKHc7nWxTDgsgJ74wgtsEiaK0NkHkZOhzdwrQtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:33:39.892629Z"},"content_sha256":"474c017d602e1165fca762e10f2cf8011209f9794a22f2e67b8caa07895c06df","schema_version":"1.0","event_id":"sha256:474c017d602e1165fca762e10f2cf8011209f9794a22f2e67b8caa07895c06df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SZV7ZARVNHWPSSKC7W6IKWU57S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.IT","math.IT"],"primary_cat":"stat.ML","authors_text":"Andre Manoel, Eric W. Tramel, Florent Krzakala, Lenka Zdeborov\\'a","submitted_at":"2017-06-02T14:45:15Z","abstract_excerpt":"In statistical learning for real-world large-scale data problems, one must often resort to \"streaming\" algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank matrix factorization. In a controlled Bayes-optimal setting, we characterize the optimal performance and phase transitions as a function of mini-batch size. We base part of our results on a detailed analysis of a mini-batch version of the approximate message-passing algorithm (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00705","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":""},"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":"2026-05-18T00:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6S1ihcF0fd1UwLyW5LhZ/2IogqRFuqmUHXaB7WaEohrNr/xnDjSXhyMtcaWPGy+bDadV0PAUFM7Ct0EhYOmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:33:39.893461Z"},"content_sha256":"215beb3b8b5d2c1d0ad2f6bd0134e9bea050c5c0076e33d292ae3b83bf59d5d3","schema_version":"1.0","event_id":"sha256:215beb3b8b5d2c1d0ad2f6bd0134e9bea050c5c0076e33d292ae3b83bf59d5d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/bundle.json","state_url":"https://pith.science/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/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":"2026-05-31T17:33:39Z","links":{"resolver":"https://pith.science/pith/SZV7ZARVNHWPSSKC7W6IKWU57S","bundle":"https://pith.science/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/bundle.json","state":"https://pith.science/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZV7ZARVNHWPSSKC7W6IKWU57S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SZV7ZARVNHWPSSKC7W6IKWU57S","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":"8058ebcbab051d0b672a9270c2b0e4303256c28c697c6b3955ae85719bc0a012","cross_cats_sorted":["cond-mat.stat-mech","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-02T14:45:15Z","title_canon_sha256":"4ab3fa10878a349ed5b2ee2155cde3c348e6e7e206cbd1788e31bd74792012ae"},"schema_version":"1.0","source":{"id":"1706.00705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00705","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00705v1","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00705","created_at":"2026-05-18T00:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"SZV7ZARVNHWP","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SZV7ZARVNHWPSSKC","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SZV7ZARV","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:215beb3b8b5d2c1d0ad2f6bd0134e9bea050c5c0076e33d292ae3b83bf59d5d3","target":"graph","created_at":"2026-05-18T00:25:34Z","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"},"paper":{"abstract_excerpt":"In statistical learning for real-world large-scale data problems, one must often resort to \"streaming\" algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank matrix factorization. In a controlled Bayes-optimal setting, we characterize the optimal performance and phase transitions as a function of mini-batch size. We base part of our results on a detailed analysis of a mini-batch version of the approximate message-passing algorithm (M","authors_text":"Andre Manoel, Eric W. Tramel, Florent Krzakala, Lenka Zdeborov\\'a","cross_cats":["cond-mat.stat-mech","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-02T14:45:15Z","title":"Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00705","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":"sha256:474c017d602e1165fca762e10f2cf8011209f9794a22f2e67b8caa07895c06df","target":"record","created_at":"2026-05-18T00:25:34Z","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":"8058ebcbab051d0b672a9270c2b0e4303256c28c697c6b3955ae85719bc0a012","cross_cats_sorted":["cond-mat.stat-mech","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-02T14:45:15Z","title_canon_sha256":"4ab3fa10878a349ed5b2ee2155cde3c348e6e7e206cbd1788e31bd74792012ae"},"schema_version":"1.0","source":{"id":"1706.00705","kind":"arxiv","version":1}},"canonical_sha256":"966bfc823569ecf94942fdbc855a9dfca0e03db71442945e78e7fce8dbb7b3a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"966bfc823569ecf94942fdbc855a9dfca0e03db71442945e78e7fce8dbb7b3a3","first_computed_at":"2026-05-18T00:25:34.350624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:34.350624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CKb4u19wls9pM1EFG6KGszRnzNI5g98gJhCxMI1PS5BoOOJawQKXkT+WbZQmPxzakCI46NJcVfy1fTr0AoQpAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:34.351364Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:474c017d602e1165fca762e10f2cf8011209f9794a22f2e67b8caa07895c06df","sha256:215beb3b8b5d2c1d0ad2f6bd0134e9bea050c5c0076e33d292ae3b83bf59d5d3"],"state_sha256":"1e0bb1219ae34f41b9618f9902f07d37fab00dc5e9f375f61e163133eac3c5ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQ/EItUesoIw+Ai7ny555z8frru/rzeQsGept1DqROAeGglYKIcSocPPLW06sVRpvhjnnkP6i6ZUscf7zs0ZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:33:39.897597Z","bundle_sha256":"0a3a801822c3dd4fbae38019962fdc30329755b36aaf0017f9f309c48f540118"}}