{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VT4WAKAENYDIZ475IBI2MKJHYD","short_pith_number":"pith:VT4WAKAE","canonical_record":{"source":{"id":"2503.07784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T19:04:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"510198acd10a8b70d478b8955e6a34bdc76452efe3d492856474f3c13807e122","abstract_canon_sha256":"cc3c02fa453b18183c5230a6dc8e69fa9d17e8047a58022fef38e3ca31835c71"},"schema_version":"1.0"},"canonical_sha256":"acf96028046e068cf3fd4051a62927c0dbc398eeb417edf90ebe777826617d14","source":{"kind":"arxiv","id":"2503.07784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07784","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07784v1","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07784","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_12","alias_value":"VT4WAKAENYDI","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"VT4WAKAENYDIZ475","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"VT4WAKAE","created_at":"2026-07-05T10:28:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VT4WAKAENYDIZ475IBI2MKJHYD","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T19:04:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"510198acd10a8b70d478b8955e6a34bdc76452efe3d492856474f3c13807e122","abstract_canon_sha256":"cc3c02fa453b18183c5230a6dc8e69fa9d17e8047a58022fef38e3ca31835c71"},"schema_version":"1.0"},"canonical_sha256":"acf96028046e068cf3fd4051a62927c0dbc398eeb417edf90ebe777826617d14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:43.598235Z","signature_b64":"hbgKww7B6z7fvp+SwKCZ5HxReKVkERSe2AR1sYwgpmxvpCqvjcnJDntBj1XeHNfvb1m9dpTGXD2OxzAMQIhGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf96028046e068cf3fd4051a62927c0dbc398eeb417edf90ebe777826617d14","last_reissued_at":"2026-07-05T10:28:43.597735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:43.597735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07784","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":"2026-07-05T10:28:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxDG/aZwFp3IZUAG6uouS/Ew0K7tuLbiVBxNJefsj/86RhbHgZw54m1bim/dDmyU9QMSR6BOIbnNH0d6qbjQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:57:36.118241Z"},"content_sha256":"fd7f4487fd1b95419554b712cbd394198ec5c2c9efc6d03754b4b3308c3813ee","schema_version":"1.0","event_id":"sha256:fd7f4487fd1b95419554b712cbd394198ec5c2c9efc6d03754b4b3308c3813ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VT4WAKAENYDIZ475IBI2MKJHYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Explainability-Performance Optimization With Surrogate Models for AI-Driven Edge Services","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Foivos Charalampakos, Iordanis Koutsopoulos, Thomas Tsouparopoulos","submitted_at":"2025-03-10T19:04:09Z","abstract_excerpt":"Explainable AI is a crucial component for edge services, as it ensures reliable decision making based on complex AI models. Surrogate models are a prominent approach of XAI where human-interpretable models, such as a linear regression model, are trained to approximate a complex (black-box) model's predictions. This paper delves into the balance between the predictive accuracy of complex AI models and their approximation by surrogate ones, advocating that both these models benefit from being learned simultaneously. We derive a joint (bi-level) training scheme for both models and we introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07784","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/2503.07784/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":"2026-07-05T10:28:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"58Pvd9inDIyaxTSVAxBcgZ5WY53Le/fLHF32ur3Ir6Nn+01fSyvo60PBjLhgosnsH/3Wsi48T1c4GD0FXtpDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:57:36.118815Z"},"content_sha256":"ba7408a9159aec86c6974fb40f71687151564a9dff02b8721c6c07ef4339688e","schema_version":"1.0","event_id":"sha256:ba7408a9159aec86c6974fb40f71687151564a9dff02b8721c6c07ef4339688e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT4WAKAENYDIZ475IBI2MKJHYD/bundle.json","state_url":"https://pith.science/pith/VT4WAKAENYDIZ475IBI2MKJHYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT4WAKAENYDIZ475IBI2MKJHYD/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":"2026-08-19T19:57:36Z","links":{"resolver":"https://pith.science/pith/VT4WAKAENYDIZ475IBI2MKJHYD","bundle":"https://pith.science/pith/VT4WAKAENYDIZ475IBI2MKJHYD/bundle.json","state":"https://pith.science/pith/VT4WAKAENYDIZ475IBI2MKJHYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT4WAKAENYDIZ475IBI2MKJHYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VT4WAKAENYDIZ475IBI2MKJHYD","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":"cc3c02fa453b18183c5230a6dc8e69fa9d17e8047a58022fef38e3ca31835c71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T19:04:09Z","title_canon_sha256":"510198acd10a8b70d478b8955e6a34bdc76452efe3d492856474f3c13807e122"},"schema_version":"1.0","source":{"id":"2503.07784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07784","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07784v1","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07784","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_12","alias_value":"VT4WAKAENYDI","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"VT4WAKAENYDIZ475","created_at":"2026-07-05T10:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"VT4WAKAE","created_at":"2026-07-05T10:28:43Z"}],"graph_snapshots":[{"event_id":"sha256:ba7408a9159aec86c6974fb40f71687151564a9dff02b8721c6c07ef4339688e","target":"graph","created_at":"2026-07-05T10:28:43Z","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/2503.07784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable AI is a crucial component for edge services, as it ensures reliable decision making based on complex AI models. Surrogate models are a prominent approach of XAI where human-interpretable models, such as a linear regression model, are trained to approximate a complex (black-box) model's predictions. This paper delves into the balance between the predictive accuracy of complex AI models and their approximation by surrogate ones, advocating that both these models benefit from being learned simultaneously. We derive a joint (bi-level) training scheme for both models and we introduce a ","authors_text":"Foivos Charalampakos, Iordanis Koutsopoulos, Thomas Tsouparopoulos","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T19:04:09Z","title":"Joint Explainability-Performance Optimization With Surrogate Models for AI-Driven Edge Services"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07784","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:fd7f4487fd1b95419554b712cbd394198ec5c2c9efc6d03754b4b3308c3813ee","target":"record","created_at":"2026-07-05T10:28:43Z","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":"cc3c02fa453b18183c5230a6dc8e69fa9d17e8047a58022fef38e3ca31835c71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T19:04:09Z","title_canon_sha256":"510198acd10a8b70d478b8955e6a34bdc76452efe3d492856474f3c13807e122"},"schema_version":"1.0","source":{"id":"2503.07784","kind":"arxiv","version":1}},"canonical_sha256":"acf96028046e068cf3fd4051a62927c0dbc398eeb417edf90ebe777826617d14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf96028046e068cf3fd4051a62927c0dbc398eeb417edf90ebe777826617d14","first_computed_at":"2026-07-05T10:28:43.597735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:43.597735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbgKww7B6z7fvp+SwKCZ5HxReKVkERSe2AR1sYwgpmxvpCqvjcnJDntBj1XeHNfvb1m9dpTGXD2OxzAMQIhGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:43.598235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd7f4487fd1b95419554b712cbd394198ec5c2c9efc6d03754b4b3308c3813ee","sha256:ba7408a9159aec86c6974fb40f71687151564a9dff02b8721c6c07ef4339688e"],"state_sha256":"1572ec7ea9e411a9129f0754c7d8acc5ee23fb6052b0c2385b17ac203598fff3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3rLDS6mjlSf4w2hD9BGk/e6J8LfH5E+LWwU78ptr59ilSDCTSB6C+r03yzQhvsmStYHmE7hKfV5SZCrEjOICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:57:36.125431Z","bundle_sha256":"346d134e0ae43f04388c5563a6871b920d724a3db8e6de6171f7cd3e15c8ef26"}}