{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IEB3XYOYOEO5I33GSBBVBGKBG5","short_pith_number":"pith:IEB3XYOY","canonical_record":{"source":{"id":"1606.05685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T21:56:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08923246883d442ba2c950e7d22ff730b767239a49a006f7716bc93398e53952","abstract_canon_sha256":"c932295c609791e0f03be4664721133d72781f61835c93d8c2871641ebbc5667"},"schema_version":"1.0"},"canonical_sha256":"4103bbe1d8711dd46f669043509941376ba988fa810aa84a31fce2620403bdea","source":{"kind":"arxiv","id":"1606.05685","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05685","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05685v2","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05685","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"IEB3XYOYOEO5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IEB3XYOYOEO5I33G","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IEB3XYOY","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IEB3XYOYOEO5I33GSBBVBGKBG5","target":"record","payload":{"canonical_record":{"source":{"id":"1606.05685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T21:56:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08923246883d442ba2c950e7d22ff730b767239a49a006f7716bc93398e53952","abstract_canon_sha256":"c932295c609791e0f03be4664721133d72781f61835c93d8c2871641ebbc5667"},"schema_version":"1.0"},"canonical_sha256":"4103bbe1d8711dd46f669043509941376ba988fa810aa84a31fce2620403bdea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:11.307331Z","signature_b64":"axAdTS4CmxnUzdouZurtl0Yi1V75A5m2j4yOB8rLkcXt5vL2E29o0zOYIAE5sOc61twksvtfUQ7JYQuBJ/Z6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4103bbe1d8711dd46f669043509941376ba988fa810aa84a31fce2620403bdea","last_reissued_at":"2026-05-18T01:12:11.306995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:11.306995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.05685","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":"2026-05-18T01:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zHArRk5dtu34i9L4Kln1+Cp3XNY34yPLVWr0OBYHywFD2QV0YGe/ufF9p1o9fl4PhMKEYcqHFCfCPwuNhoqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:07:59.433593Z"},"content_sha256":"fb3fd5fa2ef0853de820d4d5e7aa3b5f5595e08dbd2f6ec4234223ff1bdc1bf7","schema_version":"1.0","event_id":"sha256:fb3fd5fa2ef0853de820d4d5e7aa3b5f5595e08dbd2f6ec4234223ff1bdc1bf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IEB3XYOYOEO5I33GSBBVBGKBG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Visual Analytics to Interpret Predictive Machine Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Perer, Enrico Bertini, Josua Krause","submitted_at":"2016-06-17T21:56:43Z","abstract_excerpt":"It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing predictive quality. We identify a space of possible solutions and provide two examples of where such techniques have been successfully used in practice."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05685","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":"2026-05-18T01:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fj5C5tptdRUpggLZTjkYMGi41i5mNHzzk/5gXSJ2Hl3+ZLiRbUE/+cESUjAdz4S4ePzRD88Dk9K96A94cm0bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:07:59.433933Z"},"content_sha256":"eaf17ea365ca238ee0969cf1bf0536a7d9fd53b8fddb547e6fce5896f38c09f6","schema_version":"1.0","event_id":"sha256:eaf17ea365ca238ee0969cf1bf0536a7d9fd53b8fddb547e6fce5896f38c09f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/bundle.json","state_url":"https://pith.science/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/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":"2026-06-02T23:07:59Z","links":{"resolver":"https://pith.science/pith/IEB3XYOYOEO5I33GSBBVBGKBG5","bundle":"https://pith.science/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/bundle.json","state":"https://pith.science/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEB3XYOYOEO5I33GSBBVBGKBG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IEB3XYOYOEO5I33GSBBVBGKBG5","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":"c932295c609791e0f03be4664721133d72781f61835c93d8c2871641ebbc5667","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T21:56:43Z","title_canon_sha256":"08923246883d442ba2c950e7d22ff730b767239a49a006f7716bc93398e53952"},"schema_version":"1.0","source":{"id":"1606.05685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05685","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05685v2","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05685","created_at":"2026-05-18T01:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"IEB3XYOYOEO5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IEB3XYOYOEO5I33G","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IEB3XYOY","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:eaf17ea365ca238ee0969cf1bf0536a7d9fd53b8fddb547e6fce5896f38c09f6","target":"graph","created_at":"2026-05-18T01:12:11Z","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":"It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing predictive quality. We identify a space of possible solutions and provide two examples of where such techniques have been successfully used in practice.","authors_text":"Adam Perer, Enrico Bertini, Josua Krause","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T21:56:43Z","title":"Using Visual Analytics to Interpret Predictive Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05685","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:fb3fd5fa2ef0853de820d4d5e7aa3b5f5595e08dbd2f6ec4234223ff1bdc1bf7","target":"record","created_at":"2026-05-18T01:12:11Z","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":"c932295c609791e0f03be4664721133d72781f61835c93d8c2871641ebbc5667","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-17T21:56:43Z","title_canon_sha256":"08923246883d442ba2c950e7d22ff730b767239a49a006f7716bc93398e53952"},"schema_version":"1.0","source":{"id":"1606.05685","kind":"arxiv","version":2}},"canonical_sha256":"4103bbe1d8711dd46f669043509941376ba988fa810aa84a31fce2620403bdea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4103bbe1d8711dd46f669043509941376ba988fa810aa84a31fce2620403bdea","first_computed_at":"2026-05-18T01:12:11.306995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:11.306995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"axAdTS4CmxnUzdouZurtl0Yi1V75A5m2j4yOB8rLkcXt5vL2E29o0zOYIAE5sOc61twksvtfUQ7JYQuBJ/Z6Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:11.307331Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb3fd5fa2ef0853de820d4d5e7aa3b5f5595e08dbd2f6ec4234223ff1bdc1bf7","sha256:eaf17ea365ca238ee0969cf1bf0536a7d9fd53b8fddb547e6fce5896f38c09f6"],"state_sha256":"f8400fe8090d8ca7a4649e5b70d421b23bf9297b721176169511470f2c4b1280"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OEllMdyqFBPGBWIejPK4nhQus8FIVjxS/5x0TSvfCBs0DSSC6wWm9K2JZU9qmieAvkUwp/3moH3pEAmBGrRnAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:07:59.435773Z","bundle_sha256":"9e343b701fdf9ba8353003ae04cd5da40c39ebf803c5d91083db5338b4b74784"}}