{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GGLYGIZG4TVCOHLTCQ5RZVW7QE","short_pith_number":"pith:GGLYGIZG","canonical_record":{"source":{"id":"2206.05487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T10:13:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05d9a8f2ecd983b23d844fac9853340ccb339ff790725509d4c8e6df8eeae7e3","abstract_canon_sha256":"ea23bf75f03e0acd7335d4c1292bb328f0302bcf7d816f9557bc75a70ddc7b75"},"schema_version":"1.0"},"canonical_sha256":"3197832326e4ea271d73143b1cd6df8115c0a1e0413a66803e4a74a5f53105a8","source":{"kind":"arxiv","id":"2206.05487","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05487","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05487v3","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05487","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"GGLYGIZG4TVC","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_16","alias_value":"GGLYGIZG4TVCOHLT","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_8","alias_value":"GGLYGIZG","created_at":"2026-07-05T08:43:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GGLYGIZG4TVCOHLTCQ5RZVW7QE","target":"record","payload":{"canonical_record":{"source":{"id":"2206.05487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T10:13:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05d9a8f2ecd983b23d844fac9853340ccb339ff790725509d4c8e6df8eeae7e3","abstract_canon_sha256":"ea23bf75f03e0acd7335d4c1292bb328f0302bcf7d816f9557bc75a70ddc7b75"},"schema_version":"1.0"},"canonical_sha256":"3197832326e4ea271d73143b1cd6df8115c0a1e0413a66803e4a74a5f53105a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:48.627163Z","signature_b64":"dTJLdoki5qTAL7v30Psa4cTS11WAkBUKHkzn1gndi8NP1AfaQMCqjhhGQBNmkl9xrlD32DoxqEYjImflkDLTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3197832326e4ea271d73143b1cd6df8115c0a1e0413a66803e4a74a5f53105a8","last_reissued_at":"2026-07-05T08:43:48.626729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:48.626729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.05487","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pGEzYKe5XakRFXtfOJxqteXcqRK84tEke07uC61gHfpmpcJgo9YBmwINL7r/sUMjUw1i1zzONk8gvXFBN6XGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:54:12.875149Z"},"content_sha256":"0b13586f450d5ce2173a5bfcae38ab5cf9a4fc98cab182a127ff605c49131fcb","schema_version":"1.0","event_id":"sha256:0b13586f450d5ce2173a5bfcae38ab5cf9a4fc98cab182a127ff605c49131fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GGLYGIZG4TVCOHLTCQ5RZVW7QE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alvaro Tejero-Cantero, Christoph Molnar, Gunnar K\\\"onig, Timo Freiesleben","submitted_at":"2022-06-11T10:13:21Z","abstract_excerpt":"To learn about real world phenomena, scientists have traditionally used models with clearly interpretable elements. However, modern machine learning (ML) models, while powerful predictors, lack this direct elementwise interpretability (e.g. neural network weights). Interpretable machine learning (IML) offers a solution by analyzing models holistically to derive interpretations. Yet, current IML research is focused on auditing ML models rather than leveraging them for scientific inference. Our work bridges this gap, presenting a framework for designing IML methods-termed 'property descriptors' "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05487","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.05487/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T08:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHgaQGRfvG+PGmAf27NCu27Am4qf4fpXQQ2uoZULywuXBZpXOrFq1QK5Hi3BBANufLiSnV20koTreLNxNsqXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:54:12.875522Z"},"content_sha256":"7c0c25a4dd29eb4ea2f4bf79b3901e09385394e29eadf15d809d32aaa4e384b1","schema_version":"1.0","event_id":"sha256:7c0c25a4dd29eb4ea2f4bf79b3901e09385394e29eadf15d809d32aaa4e384b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/bundle.json","state_url":"https://pith.science/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/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":"2026-08-21T20:54:12Z","links":{"resolver":"https://pith.science/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE","bundle":"https://pith.science/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/bundle.json","state":"https://pith.science/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGLYGIZG4TVCOHLTCQ5RZVW7QE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GGLYGIZG4TVCOHLTCQ5RZVW7QE","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":"ea23bf75f03e0acd7335d4c1292bb328f0302bcf7d816f9557bc75a70ddc7b75","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T10:13:21Z","title_canon_sha256":"05d9a8f2ecd983b23d844fac9853340ccb339ff790725509d4c8e6df8eeae7e3"},"schema_version":"1.0","source":{"id":"2206.05487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05487","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05487v3","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05487","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"GGLYGIZG4TVC","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_16","alias_value":"GGLYGIZG4TVCOHLT","created_at":"2026-07-05T08:43:48Z"},{"alias_kind":"pith_short_8","alias_value":"GGLYGIZG","created_at":"2026-07-05T08:43:48Z"}],"graph_snapshots":[{"event_id":"sha256:7c0c25a4dd29eb4ea2f4bf79b3901e09385394e29eadf15d809d32aaa4e384b1","target":"graph","created_at":"2026-07-05T08:43:48Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.05487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To learn about real world phenomena, scientists have traditionally used models with clearly interpretable elements. However, modern machine learning (ML) models, while powerful predictors, lack this direct elementwise interpretability (e.g. neural network weights). Interpretable machine learning (IML) offers a solution by analyzing models holistically to derive interpretations. Yet, current IML research is focused on auditing ML models rather than leveraging them for scientific inference. Our work bridges this gap, presenting a framework for designing IML methods-termed 'property descriptors' ","authors_text":"Alvaro Tejero-Cantero, Christoph Molnar, Gunnar K\\\"onig, Timo Freiesleben","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T10:13:21Z","title":"Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05487","kind":"arxiv","version":3},"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":"sha256:0b13586f450d5ce2173a5bfcae38ab5cf9a4fc98cab182a127ff605c49131fcb","target":"record","created_at":"2026-07-05T08:43:48Z","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":"ea23bf75f03e0acd7335d4c1292bb328f0302bcf7d816f9557bc75a70ddc7b75","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T10:13:21Z","title_canon_sha256":"05d9a8f2ecd983b23d844fac9853340ccb339ff790725509d4c8e6df8eeae7e3"},"schema_version":"1.0","source":{"id":"2206.05487","kind":"arxiv","version":3}},"canonical_sha256":"3197832326e4ea271d73143b1cd6df8115c0a1e0413a66803e4a74a5f53105a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3197832326e4ea271d73143b1cd6df8115c0a1e0413a66803e4a74a5f53105a8","first_computed_at":"2026-07-05T08:43:48.626729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:48.626729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTJLdoki5qTAL7v30Psa4cTS11WAkBUKHkzn1gndi8NP1AfaQMCqjhhGQBNmkl9xrlD32DoxqEYjImflkDLTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:48.627163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b13586f450d5ce2173a5bfcae38ab5cf9a4fc98cab182a127ff605c49131fcb","sha256:7c0c25a4dd29eb4ea2f4bf79b3901e09385394e29eadf15d809d32aaa4e384b1"],"state_sha256":"a97085ee3250921ff12afdd9b3e77c6210330652f13356efa39706c9a697cd4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L4/59HwZaIaH9uqkwxVjyub3GmInOlb2gVh2qnjXiZ/KEwdRV0u89GdGbYpW2fGS5N1bhD0DO2n90rSZNF6rBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T20:54:12.878273Z","bundle_sha256":"645798734189054628cef4ea3a3f481ac0f3dd5419928e687345f4235c039236"}}