{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTZCYHBFYVHWSH63IVVTSQPXE5","short_pith_number":"pith:FTZCYHBF","schema_version":"1.0","canonical_sha256":"2cf22c1c25c54f691fdb456b3941f72763c1801ebf8e8e29bfc09148b647514b","source":{"kind":"arxiv","id":"2605.30601","version":1},"attestation_state":"computed","paper":{"title":"TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gesine Reinert, Micha{\\l} Kozyra","submitted_at":"2026-05-28T21:49:04Z","abstract_excerpt":"Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due to excessive or poorly structured input sensitivity. We introduce TASER (Task-Aware Stein Regularisation), a training-time regularisation framework derived from Langevin Stein operators. By penalising pointwise Stein residuals under the training distribution, TASER encourages geometric compatibility between predictors and data density, inducing anisotropic, data-aware smoothness. We provide theoretical links between Stein regularisation and reduced first-order shift sensitivity, develop scalab"},"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":"2605.30601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T21:49:04Z","cross_cats_sorted":[],"title_canon_sha256":"451c2cdb051a1c92e38d6b2090c52adcb2d0ea25aefbb9a6b7b89bf5b6b4cb03","abstract_canon_sha256":"62d5db606e3bec9f6bbe63668aae31ea6b88469c7bdaa41b36e8aa88164d36c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:03.334087Z","signature_b64":"iUFimyMJWlKD7SC7VAKSMel9UyVPJg+d3R947mxW6vneeYYziqf7ROOCZcocWtpmx7KBTNprFkZn5kwE8W5oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf22c1c25c54f691fdb456b3941f72763c1801ebf8e8e29bfc09148b647514b","last_reissued_at":"2026-06-01T01:03:03.333327Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:03.333327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gesine Reinert, Micha{\\l} Kozyra","submitted_at":"2026-05-28T21:49:04Z","abstract_excerpt":"Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due to excessive or poorly structured input sensitivity. We introduce TASER (Task-Aware Stein Regularisation), a training-time regularisation framework derived from Langevin Stein operators. By penalising pointwise Stein residuals under the training distribution, TASER encourages geometric compatibility between predictors and data density, inducing anisotropic, data-aware smoothness. We provide theoretical links between Stein regularisation and reduced first-order shift sensitivity, develop scalab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30601","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/2605.30601/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":"2605.30601","created_at":"2026-06-01T01:03:03.333437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30601v1","created_at":"2026-06-01T01:03:03.333437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30601","created_at":"2026-06-01T01:03:03.333437+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTZCYHBFYVHW","created_at":"2026-06-01T01:03:03.333437+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTZCYHBFYVHWSH63","created_at":"2026-06-01T01:03:03.333437+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTZCYHBF","created_at":"2026-06-01T01:03:03.333437+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/FTZCYHBFYVHWSH63IVVTSQPXE5","json":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5.json","graph_json":"https://pith.science/api/pith-number/FTZCYHBFYVHWSH63IVVTSQPXE5/graph.json","events_json":"https://pith.science/api/pith-number/FTZCYHBFYVHWSH63IVVTSQPXE5/events.json","paper":"https://pith.science/paper/FTZCYHBF"},"agent_actions":{"view_html":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5","download_json":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5.json","view_paper":"https://pith.science/paper/FTZCYHBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30601&json=true","fetch_graph":"https://pith.science/api/pith-number/FTZCYHBFYVHWSH63IVVTSQPXE5/graph.json","fetch_events":"https://pith.science/api/pith-number/FTZCYHBFYVHWSH63IVVTSQPXE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5/action/storage_attestation","attest_author":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5/action/author_attestation","sign_citation":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5/action/citation_signature","submit_replication":"https://pith.science/pith/FTZCYHBFYVHWSH63IVVTSQPXE5/action/replication_record"}},"created_at":"2026-06-01T01:03:03.333437+00:00","updated_at":"2026-06-01T01:03:03.333437+00:00"}