{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VZXRTA6K4ZJMKSKE5GZC24DEXL","short_pith_number":"pith:VZXRTA6K","canonical_record":{"source":{"id":"1901.03415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T22:12:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3395ea7afcc5b6d22edf2d0ee11862b6218a32d65c1c09e4d693c6de279590be","abstract_canon_sha256":"4a0562d259c2375b325e002c7d578a0ce26fd078f673ba8a321641c9c5456657"},"schema_version":"1.0"},"canonical_sha256":"ae6f1983cae652c54944e9b22d7064badf7069e353ad1d223e0e7e51e99f838c","source":{"kind":"arxiv","id":"1901.03415","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03415","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03415v2","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03415","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"VZXRTA6K4ZJM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VZXRTA6K4ZJMKSKE","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VZXRTA6K","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VZXRTA6K4ZJMKSKE5GZC24DEXL","target":"record","payload":{"canonical_record":{"source":{"id":"1901.03415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T22:12:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3395ea7afcc5b6d22edf2d0ee11862b6218a32d65c1c09e4d693c6de279590be","abstract_canon_sha256":"4a0562d259c2375b325e002c7d578a0ce26fd078f673ba8a321641c9c5456657"},"schema_version":"1.0"},"canonical_sha256":"ae6f1983cae652c54944e9b22d7064badf7069e353ad1d223e0e7e51e99f838c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:52.884214Z","signature_b64":"NpOR4JVbANezRKw7BrWQOb0v5mDlQgg63IHIAU9MP3CJiv8uyBsmnb/hby4QIu7t45Hi9Y/raEh6sGGcyqC/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae6f1983cae652c54944e9b22d7064badf7069e353ad1d223e0e7e51e99f838c","last_reissued_at":"2026-05-17T23:55:52.883754Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:52.883754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.03415","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":"2026-05-17T23:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CwUsSalqfMu9uHgWxSncl3cnYxV8VpKV5M1tmmzJ1zzYJ4xoV4Fzew2CXDCDH4KYwi7w9eMRvWJt983qgvMLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:26:03.047887Z"},"content_sha256":"dfa0da8c3c7e3d3bb5c19a0988394487a31c91e0e7bd1a2a138398608e0f21b1","schema_version":"1.0","event_id":"sha256:dfa0da8c3c7e3d3bb5c19a0988394487a31c91e0e7bd1a2a138398608e0f21b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VZXRTA6K4ZJMKSKE5GZC24DEXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Context Aware Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yun Zeng","submitted_at":"2019-01-10T22:12:24Z","abstract_excerpt":"We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts: context-free and context-sensitive. Then by employing the log-linear word production model for relating random variables to their embedding space representation and making use of the convexity of natural exponential function, we show that the embedding of an observation can also be decomposed into a weighted sum of two vectors, representing its context-free and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03415","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":"2026-05-17T23:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xr/N8IDr0ZOqcb06ojWtFpsiHY4pecRuFXdj4xwa1H7RaiXlG3UHzdY4wmgr9G0AvGBpLEgQGI5Fq/Fi3KvADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:26:03.048233Z"},"content_sha256":"1085b452380d0e7d4027795ba5885aa582510613975f81dd53237cb0d33f507b","schema_version":"1.0","event_id":"sha256:1085b452380d0e7d4027795ba5885aa582510613975f81dd53237cb0d33f507b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/bundle.json","state_url":"https://pith.science/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/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":"2026-06-09T00:26:03Z","links":{"resolver":"https://pith.science/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL","bundle":"https://pith.science/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/bundle.json","state":"https://pith.science/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZXRTA6K4ZJMKSKE5GZC24DEXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VZXRTA6K4ZJMKSKE5GZC24DEXL","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":"4a0562d259c2375b325e002c7d578a0ce26fd078f673ba8a321641c9c5456657","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T22:12:24Z","title_canon_sha256":"3395ea7afcc5b6d22edf2d0ee11862b6218a32d65c1c09e4d693c6de279590be"},"schema_version":"1.0","source":{"id":"1901.03415","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03415","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03415v2","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03415","created_at":"2026-05-17T23:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"VZXRTA6K4ZJM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VZXRTA6K4ZJMKSKE","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VZXRTA6K","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:1085b452380d0e7d4027795ba5885aa582510613975f81dd53237cb0d33f507b","target":"graph","created_at":"2026-05-17T23:55:52Z","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 propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts: context-free and context-sensitive. Then by employing the log-linear word production model for relating random variables to their embedding space representation and making use of the convexity of natural exponential function, we show that the embedding of an observation can also be decomposed into a weighted sum of two vectors, representing its context-free and ","authors_text":"Yun Zeng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T22:12:24Z","title":"Context Aware Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03415","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:dfa0da8c3c7e3d3bb5c19a0988394487a31c91e0e7bd1a2a138398608e0f21b1","target":"record","created_at":"2026-05-17T23:55:52Z","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":"4a0562d259c2375b325e002c7d578a0ce26fd078f673ba8a321641c9c5456657","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T22:12:24Z","title_canon_sha256":"3395ea7afcc5b6d22edf2d0ee11862b6218a32d65c1c09e4d693c6de279590be"},"schema_version":"1.0","source":{"id":"1901.03415","kind":"arxiv","version":2}},"canonical_sha256":"ae6f1983cae652c54944e9b22d7064badf7069e353ad1d223e0e7e51e99f838c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae6f1983cae652c54944e9b22d7064badf7069e353ad1d223e0e7e51e99f838c","first_computed_at":"2026-05-17T23:55:52.883754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:52.883754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NpOR4JVbANezRKw7BrWQOb0v5mDlQgg63IHIAU9MP3CJiv8uyBsmnb/hby4QIu7t45Hi9Y/raEh6sGGcyqC/AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:52.884214Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.03415","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfa0da8c3c7e3d3bb5c19a0988394487a31c91e0e7bd1a2a138398608e0f21b1","sha256:1085b452380d0e7d4027795ba5885aa582510613975f81dd53237cb0d33f507b"],"state_sha256":"2f8c9be869b872987edb0ec64f010026157d04bd8974b6b99c295b7583867ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fGCyb7zB3I0nO47v95RLYPSZ6poytsJv20U7BhlfGc0iCxhzBBD2PEjwIEeFibA024i4ONZT1VtMDvWerbODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:26:03.050153Z","bundle_sha256":"4d6a1a9ac30024541289aecf79bcfdb53c3cc1c62bbd50f94da10772a643b44e"}}