{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LKBFCNI3WENDFAZRW2R6EB5M5F","short_pith_number":"pith:LKBFCNI3","canonical_record":{"source":{"id":"1707.00802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-04T02:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"b3e7cfacc3258c414b4bb8fdf91af24dbf2fc119e5acfbfa3552b52059412387","abstract_canon_sha256":"f08b46ac74b1ac9a96d4ee10112269451b056d5975c7f684f54200afdea243c0"},"schema_version":"1.0"},"canonical_sha256":"5a8251351bb11a328331b6a3e207ace96f3071b8157084784e2016b3fcbb2c05","source":{"kind":"arxiv","id":"1707.00802","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00802","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00802v2","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00802","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"LKBFCNI3WEND","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LKBFCNI3WENDFAZR","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LKBFCNI3","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LKBFCNI3WENDFAZRW2R6EB5M5F","target":"record","payload":{"canonical_record":{"source":{"id":"1707.00802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-04T02:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"b3e7cfacc3258c414b4bb8fdf91af24dbf2fc119e5acfbfa3552b52059412387","abstract_canon_sha256":"f08b46ac74b1ac9a96d4ee10112269451b056d5975c7f684f54200afdea243c0"},"schema_version":"1.0"},"canonical_sha256":"5a8251351bb11a328331b6a3e207ace96f3071b8157084784e2016b3fcbb2c05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:39.692444Z","signature_b64":"PEP+XGBtTBx8D9VUYl9eRbffPJ1bNzZeYffVWSPfScvivQ8dF7YzN6KTLhvuXGnvxn+OejXi4WP5KYgVGNgwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8251351bb11a328331b6a3e207ace96f3071b8157084784e2016b3fcbb2c05","last_reissued_at":"2026-05-18T00:40:39.691598Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:39.691598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.00802","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":"2026-05-18T00:40:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMSLw01ZnSQxl5I0EwvB77iyzmgH89kJPeM4aq2RbyFibfWVUV+MWz7vtK+vqf1cCgIdQc8QuR2N/qfdcdzRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:10:34.766254Z"},"content_sha256":"a9bfb5ab2c8970f73b98db62b0094e5dcc483fa36a2491cecf140d59dcc22d8d","schema_version":"1.0","event_id":"sha256:a9bfb5ab2c8970f73b98db62b0094e5dcc483fa36a2491cecf140d59dcc22d8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LKBFCNI3WENDFAZRW2R6EB5M5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PBODL : Parallel Bayesian Online Deep Learning for Click-Through Rate Prediction in Tencent Advertising System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Zhang, Lei Xiao, Wei Xue, Xun Liu","submitted_at":"2017-07-04T02:40:41Z","abstract_excerpt":"We describe a parallel bayesian online deep learning framework (PBODL) for click-through rate (CTR) prediction within today's Tencent advertising system, which provides quick and accurate learning of user preferences. We first explain the framework with a deep probit regression model, which is trained with probabilistic back-propagation in the mode of assumed Gaussian density filtering. Then we extend the model family to a variety of bayesian online models with increasing feature embedding capabilities, such as Sparse-MLP, FM-MLP and FFM-MLP. Finally, we implement a parallel training system ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00802","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":"2026-05-18T00:40:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rE1RBGg6X1xTG4emJoShe6pcvJKbfMCM3BxVadNJx574/9JSY6DYQ1BsvQSv0aWRDfQpovTqIjUN6p/4hrYkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:10:34.766920Z"},"content_sha256":"16097d17ae54cfd54bbaa1d6680329248b2be31a6c7e451ee2553cfc5d429809","schema_version":"1.0","event_id":"sha256:16097d17ae54cfd54bbaa1d6680329248b2be31a6c7e451ee2553cfc5d429809"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/bundle.json","state_url":"https://pith.science/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/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":"2026-05-31T03:10:34Z","links":{"resolver":"https://pith.science/pith/LKBFCNI3WENDFAZRW2R6EB5M5F","bundle":"https://pith.science/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/bundle.json","state":"https://pith.science/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKBFCNI3WENDFAZRW2R6EB5M5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LKBFCNI3WENDFAZRW2R6EB5M5F","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":"f08b46ac74b1ac9a96d4ee10112269451b056d5975c7f684f54200afdea243c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-04T02:40:41Z","title_canon_sha256":"b3e7cfacc3258c414b4bb8fdf91af24dbf2fc119e5acfbfa3552b52059412387"},"schema_version":"1.0","source":{"id":"1707.00802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00802","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00802v2","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00802","created_at":"2026-05-18T00:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"LKBFCNI3WEND","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LKBFCNI3WENDFAZR","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LKBFCNI3","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:16097d17ae54cfd54bbaa1d6680329248b2be31a6c7e451ee2553cfc5d429809","target":"graph","created_at":"2026-05-18T00:40:39Z","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 parallel bayesian online deep learning framework (PBODL) for click-through rate (CTR) prediction within today's Tencent advertising system, which provides quick and accurate learning of user preferences. We first explain the framework with a deep probit regression model, which is trained with probabilistic back-propagation in the mode of assumed Gaussian density filtering. Then we extend the model family to a variety of bayesian online models with increasing feature embedding capabilities, such as Sparse-MLP, FM-MLP and FFM-MLP. Finally, we implement a parallel training system ba","authors_text":"Bo Zhang, Lei Xiao, Wei Xue, Xun Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-04T02:40:41Z","title":"PBODL : Parallel Bayesian Online Deep Learning for Click-Through Rate Prediction in Tencent Advertising System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00802","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:a9bfb5ab2c8970f73b98db62b0094e5dcc483fa36a2491cecf140d59dcc22d8d","target":"record","created_at":"2026-05-18T00:40:39Z","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":"f08b46ac74b1ac9a96d4ee10112269451b056d5975c7f684f54200afdea243c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-04T02:40:41Z","title_canon_sha256":"b3e7cfacc3258c414b4bb8fdf91af24dbf2fc119e5acfbfa3552b52059412387"},"schema_version":"1.0","source":{"id":"1707.00802","kind":"arxiv","version":2}},"canonical_sha256":"5a8251351bb11a328331b6a3e207ace96f3071b8157084784e2016b3fcbb2c05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a8251351bb11a328331b6a3e207ace96f3071b8157084784e2016b3fcbb2c05","first_computed_at":"2026-05-18T00:40:39.691598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:39.691598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PEP+XGBtTBx8D9VUYl9eRbffPJ1bNzZeYffVWSPfScvivQ8dF7YzN6KTLhvuXGnvxn+OejXi4WP5KYgVGNgwDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:39.692444Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.00802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9bfb5ab2c8970f73b98db62b0094e5dcc483fa36a2491cecf140d59dcc22d8d","sha256:16097d17ae54cfd54bbaa1d6680329248b2be31a6c7e451ee2553cfc5d429809"],"state_sha256":"5b452b1c0dd7d1beba7386e3e899886ace509dab6ecca42690cec50630498451"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pk/wG/HNH4Np58nlQhb60IjkjDL/8JXe6KB0YBjGoJY4uFigI3rjuWaUSfhHyAVwKGuphuS/uLg+M8OurfnhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:10:34.770575Z","bundle_sha256":"bdd13697c8f46d6a294b06f9d318a7920ae5b82b5da1280c95898c3a705a9127"}}