{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3MWOYPZ3EQH2NLFDKCC2WCVPSF","short_pith_number":"pith:3MWOYPZ3","canonical_record":{"source":{"id":"1612.04898","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-15T01:00:23Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"a465ecf02fde36d8aa0f6bab701c32fa0839928b4362b2dd6aa4df32d108d840","abstract_canon_sha256":"e494038edce33a12d8ba5ec5616ff00682fb0e9fd214574c2bdc216d2617442b"},"schema_version":"1.0"},"canonical_sha256":"db2cec3f3b240fa6aca35085ab0aaf914eab31bea078eb4f756da4d9efb7cc92","source":{"kind":"arxiv","id":"1612.04898","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.04898","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"1612.04898v2","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04898","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"3MWOYPZ3EQH2","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3MWOYPZ3EQH2NLFD","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3MWOYPZ3","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3MWOYPZ3EQH2NLFDKCC2WCVPSF","target":"record","payload":{"canonical_record":{"source":{"id":"1612.04898","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-15T01:00:23Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"a465ecf02fde36d8aa0f6bab701c32fa0839928b4362b2dd6aa4df32d108d840","abstract_canon_sha256":"e494038edce33a12d8ba5ec5616ff00682fb0e9fd214574c2bdc216d2617442b"},"schema_version":"1.0"},"canonical_sha256":"db2cec3f3b240fa6aca35085ab0aaf914eab31bea078eb4f756da4d9efb7cc92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:41.392169Z","signature_b64":"bNzK5uKSHEnBQ6maVBqfkdwIDgMRrJgMk8v75XKoV5/DoPqVJ37Tn075l8H/BUahd0IOog1ke20UOuiF7I92Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db2cec3f3b240fa6aca35085ab0aaf914eab31bea078eb4f756da4d9efb7cc92","last_reissued_at":"2026-05-18T00:14:41.391549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:41.391549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.04898","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wy9v1CXB+Q+V1j/SPtiT1397py+NSdk45a06gFWfFRDU5vIQkxVj671qWTeBb7r+oJP5k5riwtbYirqJKLGaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:30:03.080312Z"},"content_sha256":"c561d4f4fffea178b31c5104950abef848193e294ab05b2387dd0d093b4d54e2","schema_version":"1.0","event_id":"sha256:c561d4f4fffea178b31c5104950abef848193e294ab05b2387dd0d093b4d54e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3MWOYPZ3EQH2NLFDKCC2WCVPSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"stat.ML","authors_text":"Garrett Kenyon, Jeffrey Bilmes, Sunil Thulasidasan","submitted_at":"2016-12-15T01:00:23Z","abstract_excerpt":"We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a technique, first described in [13] for the construction of mini-batches for stochastic gradient descent (SGD) based on synthesized partitions of an affinity graph that are consistent with the graph structure, but also preserve enough stochasticity for convergence of SGD to good local minima. We show how our technique allows a graph-based semi-supervised loss function to be decomposed i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04898","kind":"arxiv","version":2},"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":"2026-05-18T00:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qqD9rO9upwbWuMKmwJXh6F+5vgF+NcQFgLpLcYlgIODd+4Ouhb2RA+npn7biga2EsRF6pWxjs/ducB0qCUVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:30:03.080966Z"},"content_sha256":"f21c594083e0dc6ae270e90083358874f708beb4d91e1aa6423d562b05219297","schema_version":"1.0","event_id":"sha256:f21c594083e0dc6ae270e90083358874f708beb4d91e1aa6423d562b05219297"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/bundle.json","state_url":"https://pith.science/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/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":"2026-05-23T21:30:03Z","links":{"resolver":"https://pith.science/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF","bundle":"https://pith.science/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/bundle.json","state":"https://pith.science/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MWOYPZ3EQH2NLFDKCC2WCVPSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3MWOYPZ3EQH2NLFDKCC2WCVPSF","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":"e494038edce33a12d8ba5ec5616ff00682fb0e9fd214574c2bdc216d2617442b","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-15T01:00:23Z","title_canon_sha256":"a465ecf02fde36d8aa0f6bab701c32fa0839928b4362b2dd6aa4df32d108d840"},"schema_version":"1.0","source":{"id":"1612.04898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.04898","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"1612.04898v2","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04898","created_at":"2026-05-18T00:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"3MWOYPZ3EQH2","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3MWOYPZ3EQH2NLFD","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3MWOYPZ3","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:f21c594083e0dc6ae270e90083358874f708beb4d91e1aa6423d562b05219297","target":"graph","created_at":"2026-05-18T00:14:41Z","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":"We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a technique, first described in [13] for the construction of mini-batches for stochastic gradient descent (SGD) based on synthesized partitions of an affinity graph that are consistent with the graph structure, but also preserve enough stochasticity for convergence of SGD to good local minima. We show how our technique allows a graph-based semi-supervised loss function to be decomposed i","authors_text":"Garrett Kenyon, Jeffrey Bilmes, Sunil Thulasidasan","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-15T01:00:23Z","title":"Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04898","kind":"arxiv","version":2},"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:c561d4f4fffea178b31c5104950abef848193e294ab05b2387dd0d093b4d54e2","target":"record","created_at":"2026-05-18T00:14:41Z","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":"e494038edce33a12d8ba5ec5616ff00682fb0e9fd214574c2bdc216d2617442b","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-15T01:00:23Z","title_canon_sha256":"a465ecf02fde36d8aa0f6bab701c32fa0839928b4362b2dd6aa4df32d108d840"},"schema_version":"1.0","source":{"id":"1612.04898","kind":"arxiv","version":2}},"canonical_sha256":"db2cec3f3b240fa6aca35085ab0aaf914eab31bea078eb4f756da4d9efb7cc92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db2cec3f3b240fa6aca35085ab0aaf914eab31bea078eb4f756da4d9efb7cc92","first_computed_at":"2026-05-18T00:14:41.391549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:41.391549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bNzK5uKSHEnBQ6maVBqfkdwIDgMRrJgMk8v75XKoV5/DoPqVJ37Tn075l8H/BUahd0IOog1ke20UOuiF7I92Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:41.392169Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.04898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c561d4f4fffea178b31c5104950abef848193e294ab05b2387dd0d093b4d54e2","sha256:f21c594083e0dc6ae270e90083358874f708beb4d91e1aa6423d562b05219297"],"state_sha256":"a91e6cc20ecd07f665655361a5805728c4ce3643d0f282f7d87a328e8faa6f8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8QexlAxHKmGj3aQZ8PDHVso+Q8nS2uJsK3LTVxMEQJJoZdApVvjg1s4IXUKRxLWPA74IhV7aJJINA+S+45hAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T21:30:03.084597Z","bundle_sha256":"3b56866e07a41ba65e45d262dae374c0ff2c697d73e2d818a7099ea48234aee6"}}