{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EBJ54EPXVW5DWMLLHAK6P6IT3M","short_pith_number":"pith:EBJ54EPX","canonical_record":{"source":{"id":"2408.05060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T13:30:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2104a19253d3ce308a2cc8d8c823e700bffc9adcfd790321d6323f02683a86a","abstract_canon_sha256":"73de9e5d3b1a4b626a91abfa3eee4af75993a97295d5fde30cd0ffb5838f61f4"},"schema_version":"1.0"},"canonical_sha256":"2053de11f7adba3b316b3815e7f913db340e2e479c82494063a18edb1bfe6135","source":{"kind":"arxiv","id":"2408.05060","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05060","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05060v1","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05060","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"EBJ54EPXVW5D","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_16","alias_value":"EBJ54EPXVW5DWMLL","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_8","alias_value":"EBJ54EPX","created_at":"2026-07-05T08:53:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EBJ54EPXVW5DWMLLHAK6P6IT3M","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T13:30:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2104a19253d3ce308a2cc8d8c823e700bffc9adcfd790321d6323f02683a86a","abstract_canon_sha256":"73de9e5d3b1a4b626a91abfa3eee4af75993a97295d5fde30cd0ffb5838f61f4"},"schema_version":"1.0"},"canonical_sha256":"2053de11f7adba3b316b3815e7f913db340e2e479c82494063a18edb1bfe6135","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:56.188076Z","signature_b64":"zWo7VsDfT9USVbwbEDcwHXiSWC7klDHyjKYx9oEDX859R6ocqM/mE+luw4/wNIGLPlc74M5tXO7jKoanzr3dBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2053de11f7adba3b316b3815e7f913db340e2e479c82494063a18edb1bfe6135","last_reissued_at":"2026-07-05T08:53:56.187602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:56.187602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05060","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":"2026-07-05T08:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TG8N/9JIh6xYSmssYr+yflC4oIH6SpfNMcQzQ412tg8CfwP8FEegBz296bLd76PZCvLXhhds/dxuNpHtkC9KDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:35:28.429338Z"},"content_sha256":"b8f33431a0c2ec086db0a77a88bcf4b4fc724e0cf3cf3edd968c5f4f68140740","schema_version":"1.0","event_id":"sha256:b8f33431a0c2ec086db0a77a88bcf4b4fc724e0cf3cf3edd968c5f4f68140740"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EBJ54EPXVW5DWMLLHAK6P6IT3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLEAMS: Bridging the Gap Between Local and Global Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damien Garreau, Giorgio Visani, Vincenzo Stanzione","submitted_at":"2024-08-09T13:30:37Z","abstract_excerpt":"The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these methods require recalculating explanations for each example. On the other side, while there exist global approaches they often produce explanations that are either overly simplistic and unreliable or excessively complex. To bridge this gap, we propose GLEAMS, a novel method that partitions the input space and learns an interpretable model within each sub-region,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05060","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.05060/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":"2026-07-05T08:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HkxggWsh0ovbnmcfTTaPPmA6t2p/ZRh8HCH+0bIyvUhJmWMqCFF64eGggqcbTSccDl0RfWJxZbVlUPXCdQYdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T02:35:28.429819Z"},"content_sha256":"b5f441811cd89de4a64292b4a5969f5c6dea223123a211092fbc167db618f442","schema_version":"1.0","event_id":"sha256:b5f441811cd89de4a64292b4a5969f5c6dea223123a211092fbc167db618f442"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/bundle.json","state_url":"https://pith.science/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/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":"2026-08-10T02:35:28Z","links":{"resolver":"https://pith.science/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M","bundle":"https://pith.science/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/bundle.json","state":"https://pith.science/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBJ54EPXVW5DWMLLHAK6P6IT3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBJ54EPXVW5DWMLLHAK6P6IT3M","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":"73de9e5d3b1a4b626a91abfa3eee4af75993a97295d5fde30cd0ffb5838f61f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T13:30:37Z","title_canon_sha256":"d2104a19253d3ce308a2cc8d8c823e700bffc9adcfd790321d6323f02683a86a"},"schema_version":"1.0","source":{"id":"2408.05060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05060","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05060v1","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05060","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"EBJ54EPXVW5D","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_16","alias_value":"EBJ54EPXVW5DWMLL","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_8","alias_value":"EBJ54EPX","created_at":"2026-07-05T08:53:56Z"}],"graph_snapshots":[{"event_id":"sha256:b5f441811cd89de4a64292b4a5969f5c6dea223123a211092fbc167db618f442","target":"graph","created_at":"2026-07-05T08:53:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.05060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these methods require recalculating explanations for each example. On the other side, while there exist global approaches they often produce explanations that are either overly simplistic and unreliable or excessively complex. To bridge this gap, we propose GLEAMS, a novel method that partitions the input space and learns an interpretable model within each sub-region,","authors_text":"Damien Garreau, Giorgio Visani, Vincenzo Stanzione","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T13:30:37Z","title":"GLEAMS: Bridging the Gap Between Local and Global Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05060","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:b8f33431a0c2ec086db0a77a88bcf4b4fc724e0cf3cf3edd968c5f4f68140740","target":"record","created_at":"2026-07-05T08:53:56Z","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":"73de9e5d3b1a4b626a91abfa3eee4af75993a97295d5fde30cd0ffb5838f61f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T13:30:37Z","title_canon_sha256":"d2104a19253d3ce308a2cc8d8c823e700bffc9adcfd790321d6323f02683a86a"},"schema_version":"1.0","source":{"id":"2408.05060","kind":"arxiv","version":1}},"canonical_sha256":"2053de11f7adba3b316b3815e7f913db340e2e479c82494063a18edb1bfe6135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2053de11f7adba3b316b3815e7f913db340e2e479c82494063a18edb1bfe6135","first_computed_at":"2026-07-05T08:53:56.187602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:56.187602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zWo7VsDfT9USVbwbEDcwHXiSWC7klDHyjKYx9oEDX859R6ocqM/mE+luw4/wNIGLPlc74M5tXO7jKoanzr3dBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:56.188076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8f33431a0c2ec086db0a77a88bcf4b4fc724e0cf3cf3edd968c5f4f68140740","sha256:b5f441811cd89de4a64292b4a5969f5c6dea223123a211092fbc167db618f442"],"state_sha256":"034a7a93341cf9881af3a0daae5aad1bff3de4b349ea3779cb5e1e7493d38e5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKSs+NUZgL6xV7Zbo4PnPuW7JZBdbIyEptOOYAbrWXTKj6r9s0BC34sOnrFcu1Vg1ekVZCrMFtvrXo0zcFYJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T02:35:28.434068Z","bundle_sha256":"cd07ad41263454da4d1f62ae1ef8712904533a14bf2e87769f449475d570c157"}}