{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IJXC233UHU6MG2PQ3DSGLVVIL6","short_pith_number":"pith:IJXC233U","schema_version":"1.0","canonical_sha256":"426e2d6f743d3cc369f0d8e465d6a85fa47fc5da616b1014feabde0f32decf15","source":{"kind":"arxiv","id":"2305.13271","version":2},"attestation_state":"computed","paper":{"title":"MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Charles Arnal, Felix Hensel, Fr\\'ed\\'eric Chazal, Hiroaki Kurihara, Mathieu Carri\\`ere, Th\\'eo Lacombe, Yuichi Ike","submitted_at":"2023-05-22T17:34:47Z","abstract_excerpt":"Despite their successful application to a variety of tasks, neural networks remain limited, like other machine learning methods, by their sensitivity to shifts in the data: their performance can be severely impacted by differences in distribution between the data on which they were trained and that on which they are deployed. In this article, we propose a new family of representations, called MAGDiff, that we extract from any given neural network classifier and that allows for efficient covariate data shift detection without the need to train a new model dedicated to this task. These represent"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.13271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-22T17:34:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b4c18b442081137c501fb02a2c02595238c6b66dede0510a5e00a9409eadf9bd","abstract_canon_sha256":"f571be024fa760b626f64d9dd59b77750479ad70ea3614411ad56ac18f5141ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:57.144490Z","signature_b64":"+/188LzAYP10zJsqOCpggLHgnI+w27yz/LpTF4t1/bbB/g5pzt0j8ePvN78A06NkgLVoCKFww1/kZcZ/9+6rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426e2d6f743d3cc369f0d8e465d6a85fa47fc5da616b1014feabde0f32decf15","last_reissued_at":"2026-07-05T08:17:57.144066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:57.144066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAGDiff: Covariate Data Set Shift Detection via Activation Graphs of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Charles Arnal, Felix Hensel, Fr\\'ed\\'eric Chazal, Hiroaki Kurihara, Mathieu Carri\\`ere, Th\\'eo Lacombe, Yuichi Ike","submitted_at":"2023-05-22T17:34:47Z","abstract_excerpt":"Despite their successful application to a variety of tasks, neural networks remain limited, like other machine learning methods, by their sensitivity to shifts in the data: their performance can be severely impacted by differences in distribution between the data on which they were trained and that on which they are deployed. In this article, we propose a new family of representations, called MAGDiff, that we extract from any given neural network classifier and that allows for efficient covariate data shift detection without the need to train a new model dedicated to this task. These represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13271","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.13271/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.13271","created_at":"2026-07-05T08:17:57.144120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13271v2","created_at":"2026-07-05T08:17:57.144120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13271","created_at":"2026-07-05T08:17:57.144120+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJXC233UHU6M","created_at":"2026-07-05T08:17:57.144120+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJXC233UHU6MG2PQ","created_at":"2026-07-05T08:17:57.144120+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJXC233U","created_at":"2026-07-05T08:17:57.144120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6","json":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6.json","graph_json":"https://pith.science/api/pith-number/IJXC233UHU6MG2PQ3DSGLVVIL6/graph.json","events_json":"https://pith.science/api/pith-number/IJXC233UHU6MG2PQ3DSGLVVIL6/events.json","paper":"https://pith.science/paper/IJXC233U"},"agent_actions":{"view_html":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6","download_json":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6.json","view_paper":"https://pith.science/paper/IJXC233U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13271&json=true","fetch_graph":"https://pith.science/api/pith-number/IJXC233UHU6MG2PQ3DSGLVVIL6/graph.json","fetch_events":"https://pith.science/api/pith-number/IJXC233UHU6MG2PQ3DSGLVVIL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6/action/storage_attestation","attest_author":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6/action/author_attestation","sign_citation":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6/action/citation_signature","submit_replication":"https://pith.science/pith/IJXC233UHU6MG2PQ3DSGLVVIL6/action/replication_record"}},"created_at":"2026-07-05T08:17:57.144120+00:00","updated_at":"2026-07-05T08:17:57.144120+00:00"}