{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HVHG72QWCGTC2WVUZUQM7KDSCG","short_pith_number":"pith:HVHG72QW","canonical_record":{"source":{"id":"1801.04295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-12T19:26:35Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"0ab9f3946906459b025f2bc92453ccb46d5320036933644d27e068d192da4e4a","abstract_canon_sha256":"fd33d652bb0a1414815242bf560426ff1f373a1468a2246277d299924fcb4c5c"},"schema_version":"1.0"},"canonical_sha256":"3d4e6fea1611a62d5ab4cd20cfa87211be463939ce0d1d207e696b043a1c3eaf","source":{"kind":"arxiv","id":"1801.04295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04295","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04295v1","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04295","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"HVHG72QWCGTC","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HVHG72QWCGTC2WVU","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HVHG72QW","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HVHG72QWCGTC2WVUZUQM7KDSCG","target":"record","payload":{"canonical_record":{"source":{"id":"1801.04295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-12T19:26:35Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"0ab9f3946906459b025f2bc92453ccb46d5320036933644d27e068d192da4e4a","abstract_canon_sha256":"fd33d652bb0a1414815242bf560426ff1f373a1468a2246277d299924fcb4c5c"},"schema_version":"1.0"},"canonical_sha256":"3d4e6fea1611a62d5ab4cd20cfa87211be463939ce0d1d207e696b043a1c3eaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:06.975877Z","signature_b64":"nfbjXzxvLvznLJLt7V7zT4Q9m+I3BE3yuryyc2i0amVKdnlHhxu6LTCUqAreCma6bzMahOu6lGpsZval2UxEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4e6fea1611a62d5ab4cd20cfa87211be463939ce0d1d207e696b043a1c3eaf","last_reissued_at":"2026-05-18T00:26:06.974995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:06.974995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.04295","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":"2026-05-18T00:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ep366M4bzIhmO0HiE8O943LLmzvtYuGEVH7O5NmH4PgTZFZ1NXErNMVGvCfjp8YVjI12NiBzhDMNlDH0EKYgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:27:09.404496Z"},"content_sha256":"4409df7ee0e8778ae59cc61ba0bc6bb751abfe6e87b10b2c920c6c03e7798ba1","schema_version":"1.0","event_id":"sha256:4409df7ee0e8778ae59cc61ba0bc6bb751abfe6e87b10b2c920c6c03e7798ba1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HVHG72QWCGTC2WVUZUQM7KDSCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization Error Bounds for Noisy, Iterative Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Pensia, Po-Ling Loh, Varun Jog","submitted_at":"2018-01-12T19:26:35Z","abstract_excerpt":"In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the generalization error of empirical risk minimization based on the mutual information $I(S;W)$ between the algorithm input $S$ and the algorithm output $W$, when the loss function is sub-Gaussian. We leverage these results to derive generalization error bounds for a broad class of iterative algorithms that are characterized by bounded, noisy updates with Markovian stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04295","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":"2026-05-18T00:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMg2ch6eimNYmmRLx5HWxH2Zq8cqLx18FSRcV4PgqskKSXH09jCxRPsoyXNV2JyalQJL8r0z5aO3638cV5fmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:27:09.404845Z"},"content_sha256":"dc49bd59f340385b9de6af75360eed998fec1eb71b6d7c1a638531cd44c4219b","schema_version":"1.0","event_id":"sha256:dc49bd59f340385b9de6af75360eed998fec1eb71b6d7c1a638531cd44c4219b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/bundle.json","state_url":"https://pith.science/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/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":"2026-06-03T08:27:09Z","links":{"resolver":"https://pith.science/pith/HVHG72QWCGTC2WVUZUQM7KDSCG","bundle":"https://pith.science/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/bundle.json","state":"https://pith.science/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HVHG72QWCGTC2WVUZUQM7KDSCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HVHG72QWCGTC2WVUZUQM7KDSCG","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":"fd33d652bb0a1414815242bf560426ff1f373a1468a2246277d299924fcb4c5c","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-12T19:26:35Z","title_canon_sha256":"0ab9f3946906459b025f2bc92453ccb46d5320036933644d27e068d192da4e4a"},"schema_version":"1.0","source":{"id":"1801.04295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.04295","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"1801.04295v1","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.04295","created_at":"2026-05-18T00:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"HVHG72QWCGTC","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HVHG72QWCGTC2WVU","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HVHG72QW","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:dc49bd59f340385b9de6af75360eed998fec1eb71b6d7c1a638531cd44c4219b","target":"graph","created_at":"2026-05-18T00:26:06Z","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 theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bound on the generalization error of empirical risk minimization based on the mutual information $I(S;W)$ between the algorithm input $S$ and the algorithm output $W$, when the loss function is sub-Gaussian. We leverage these results to derive generalization error bounds for a broad class of iterative algorithms that are characterized by bounded, noisy updates with Markovian stru","authors_text":"Ankit Pensia, Po-Ling Loh, Varun Jog","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-12T19:26:35Z","title":"Generalization Error Bounds for Noisy, Iterative Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.04295","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":"sha256:4409df7ee0e8778ae59cc61ba0bc6bb751abfe6e87b10b2c920c6c03e7798ba1","target":"record","created_at":"2026-05-18T00:26:06Z","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":"fd33d652bb0a1414815242bf560426ff1f373a1468a2246277d299924fcb4c5c","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-12T19:26:35Z","title_canon_sha256":"0ab9f3946906459b025f2bc92453ccb46d5320036933644d27e068d192da4e4a"},"schema_version":"1.0","source":{"id":"1801.04295","kind":"arxiv","version":1}},"canonical_sha256":"3d4e6fea1611a62d5ab4cd20cfa87211be463939ce0d1d207e696b043a1c3eaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d4e6fea1611a62d5ab4cd20cfa87211be463939ce0d1d207e696b043a1c3eaf","first_computed_at":"2026-05-18T00:26:06.974995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:06.974995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nfbjXzxvLvznLJLt7V7zT4Q9m+I3BE3yuryyc2i0amVKdnlHhxu6LTCUqAreCma6bzMahOu6lGpsZval2UxEBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:06.975877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.04295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4409df7ee0e8778ae59cc61ba0bc6bb751abfe6e87b10b2c920c6c03e7798ba1","sha256:dc49bd59f340385b9de6af75360eed998fec1eb71b6d7c1a638531cd44c4219b"],"state_sha256":"f319f408d6b85b11a7c410c2cb25737daea216624f86947e96dad78445f3d1c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LRvRw6/D1/YiTJGDkNLa4NZ5pwgVS+Lz2LnovL0ypl1n6cvNR2mL43j9L5O9hPni7aqttu4EyCRVz9+Q+yfeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:27:09.406850Z","bundle_sha256":"34b8ee7514ede7a0be8f399db5a0239cea4fa922e1bda18dad38e2346d1a9be1"}}