{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4JQQPMG7QHJPGLZRFXSMJNTB7L","short_pith_number":"pith:4JQQPMG7","canonical_record":{"source":{"id":"1903.02013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T19:02:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a3f16740f7e6f5a7f463d0562669475d6959f64e1caf0afddcea54579298195","abstract_canon_sha256":"84854a101f43f664e7722857965c5f17f5e41d1420c707e97a116840e967f4c0"},"schema_version":"1.0"},"canonical_sha256":"e26107b0df81d2f32f312de4c4b661faf6c3ad0e22bde0787a9528e8c98f331e","source":{"kind":"arxiv","id":"1903.02013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02013","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02013v1","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02013","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"pith_short_12","alias_value":"4JQQPMG7QHJP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4JQQPMG7QHJPGLZR","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4JQQPMG7","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4JQQPMG7QHJPGLZRFXSMJNTB7L","target":"record","payload":{"canonical_record":{"source":{"id":"1903.02013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T19:02:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a3f16740f7e6f5a7f463d0562669475d6959f64e1caf0afddcea54579298195","abstract_canon_sha256":"84854a101f43f664e7722857965c5f17f5e41d1420c707e97a116840e967f4c0"},"schema_version":"1.0"},"canonical_sha256":"e26107b0df81d2f32f312de4c4b661faf6c3ad0e22bde0787a9528e8c98f331e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:56.862947Z","signature_b64":"htPjg7Ch1LZc3aPZ4WCf3THFpaWdaYoSZyips/77unISpDnDazpH1fApSTb3kcLc4rnD0IM36coA4V2GLwqoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26107b0df81d2f32f312de4c4b661faf6c3ad0e22bde0787a9528e8c98f331e","last_reissued_at":"2026-05-17T23:51:56.862500Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:56.862500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.02013","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":"2026-05-17T23:51:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pN6giJZfr/O/Lk8AVKkcNv+DdtvZyUr+GHD38kpejwSiiINPkHkAMJ02CeJi7rIXFb99dtDiIysYVim47FHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:08:49.258847Z"},"content_sha256":"4e835c3b9946bdbaa0f2ed9cf23985e758820daa11075288877add090a276da0","schema_version":"1.0","event_id":"sha256:4e835c3b9946bdbaa0f2ed9cf23985e758820daa11075288877add090a276da0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4JQQPMG7QHJPGLZRFXSMJNTB7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PROPS: Probabilistic personalization of black-box sequence models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Michael Thomas Wojnowicz, Xuan Zhao","submitted_at":"2019-03-05T19:02:11Z","abstract_excerpt":"We present PROPS, a lightweight transfer learning mechanism for sequential data. PROPS learns probabilistic perturbations around the predictions of one or more arbitrarily complex, pre-trained black box models (such as recurrent neural networks). The technique pins the black-box prediction functions to \"source nodes\" of a hidden Markov model (HMM), and uses the remaining nodes as \"perturbation nodes\" for learning customized perturbations around those predictions. In this paper, we describe the PROPS model, provide an algorithm for online learning of its parameters, and demonstrate the consiste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02013","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":"2026-05-17T23:51:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4U0jBLumEWw3uLxnNV7o1gEa1eS9GBH2JCj9DyoUMKEPM3Cg45qd1rkTbFpGceNwSOKa/VEZNpte22CtXYoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:08:49.259191Z"},"content_sha256":"e095be193f81d0244087ddea4a19c81f35ac6c534dc46018f5ff7a391bc34ae4","schema_version":"1.0","event_id":"sha256:e095be193f81d0244087ddea4a19c81f35ac6c534dc46018f5ff7a391bc34ae4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/bundle.json","state_url":"https://pith.science/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/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":"2026-06-02T08:08:49Z","links":{"resolver":"https://pith.science/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L","bundle":"https://pith.science/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/bundle.json","state":"https://pith.science/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JQQPMG7QHJPGLZRFXSMJNTB7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4JQQPMG7QHJPGLZRFXSMJNTB7L","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":"84854a101f43f664e7722857965c5f17f5e41d1420c707e97a116840e967f4c0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T19:02:11Z","title_canon_sha256":"4a3f16740f7e6f5a7f463d0562669475d6959f64e1caf0afddcea54579298195"},"schema_version":"1.0","source":{"id":"1903.02013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02013","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02013v1","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02013","created_at":"2026-05-17T23:51:56Z"},{"alias_kind":"pith_short_12","alias_value":"4JQQPMG7QHJP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4JQQPMG7QHJPGLZR","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4JQQPMG7","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:e095be193f81d0244087ddea4a19c81f35ac6c534dc46018f5ff7a391bc34ae4","target":"graph","created_at":"2026-05-17T23:51:56Z","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 present PROPS, a lightweight transfer learning mechanism for sequential data. PROPS learns probabilistic perturbations around the predictions of one or more arbitrarily complex, pre-trained black box models (such as recurrent neural networks). The technique pins the black-box prediction functions to \"source nodes\" of a hidden Markov model (HMM), and uses the remaining nodes as \"perturbation nodes\" for learning customized perturbations around those predictions. In this paper, we describe the PROPS model, provide an algorithm for online learning of its parameters, and demonstrate the consiste","authors_text":"Michael Thomas Wojnowicz, Xuan Zhao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T19:02:11Z","title":"PROPS: Probabilistic personalization of black-box sequence models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02013","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":"sha256:4e835c3b9946bdbaa0f2ed9cf23985e758820daa11075288877add090a276da0","target":"record","created_at":"2026-05-17T23:51:56Z","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":"84854a101f43f664e7722857965c5f17f5e41d1420c707e97a116840e967f4c0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-05T19:02:11Z","title_canon_sha256":"4a3f16740f7e6f5a7f463d0562669475d6959f64e1caf0afddcea54579298195"},"schema_version":"1.0","source":{"id":"1903.02013","kind":"arxiv","version":1}},"canonical_sha256":"e26107b0df81d2f32f312de4c4b661faf6c3ad0e22bde0787a9528e8c98f331e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e26107b0df81d2f32f312de4c4b661faf6c3ad0e22bde0787a9528e8c98f331e","first_computed_at":"2026-05-17T23:51:56.862500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:56.862500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"htPjg7Ch1LZc3aPZ4WCf3THFpaWdaYoSZyips/77unISpDnDazpH1fApSTb3kcLc4rnD0IM36coA4V2GLwqoCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:56.862947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.02013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e835c3b9946bdbaa0f2ed9cf23985e758820daa11075288877add090a276da0","sha256:e095be193f81d0244087ddea4a19c81f35ac6c534dc46018f5ff7a391bc34ae4"],"state_sha256":"5fe87ee89195512ad2cd3d86f71ec7dbf0f961bfeff81cf52ddd68920ccf8f78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yxQne6gvs734jeamGeqPActTRE3zIlGD1MntE3beboBExvH/L+rYrXwiSJtqtvv+XHEz96imaKp/6/7H/H1MCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T08:08:49.261562Z","bundle_sha256":"6443dc583ed674b3411fce20b9c9982c91a15504698e229dce74cab2206f1173"}}