{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NBYYI5475C5HD35HZTCUKKUGJ4","short_pith_number":"pith:NBYYI547","schema_version":"1.0","canonical_sha256":"687184779fe8ba71efa7ccc5452a864f16ccace7ece19f33e60b919a6f652604","source":{"kind":"arxiv","id":"2505.06258","version":1},"attestation_state":"computed","paper":{"title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Chen, Jianlong Zhou, Jiayu Zhang, Zhibo Jin, Zhiyu Zhu","submitted_at":"2025-05-03T12:00:59Z","abstract_excerpt":"Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate multiple attribution methods but suffer from scalability limitations, high coupling, theoretical constraints, and lack of user-friendly implementations, hindering neural network transparency and interoperability. To address these challenges, we propose Attribution-Based Explainability (ABE), a unified framework that formalizes Fundamental Attribution Methods and in"},"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":"2505.06258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-03T12:00:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58a503a4481b8e9ceb6ed1c657044c226524b2370c428d53241ec0e4eee8978b","abstract_canon_sha256":"586b5e258f50a10be93c5ec3c838c36a61b6bfa68ceb54909351dc7cbf9868cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:06.137753Z","signature_b64":"oKlW2GDcbONlrpH/T1OqlZd9Tubz/ZdaSMS0ik/VqKyrebcO34LAD4Rvr2XADXQDcXxMpjZiCKOL7/opTqH3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687184779fe8ba71efa7ccc5452a864f16ccace7ece19f33e60b919a6f652604","last_reissued_at":"2026-07-05T11:01:06.137252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:06.137252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Chen, Jianlong Zhou, Jiayu Zhang, Zhibo Jin, Zhiyu Zhu","submitted_at":"2025-05-03T12:00:59Z","abstract_excerpt":"Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate multiple attribution methods but suffer from scalability limitations, high coupling, theoretical constraints, and lack of user-friendly implementations, hindering neural network transparency and interoperability. To address these challenges, we propose Attribution-Based Explainability (ABE), a unified framework that formalizes Fundamental Attribution Methods and in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06258","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/2505.06258/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":"2505.06258","created_at":"2026-07-05T11:01:06.137311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06258v1","created_at":"2026-07-05T11:01:06.137311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06258","created_at":"2026-07-05T11:01:06.137311+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBYYI5475C5H","created_at":"2026-07-05T11:01:06.137311+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBYYI5475C5HD35H","created_at":"2026-07-05T11:01:06.137311+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBYYI547","created_at":"2026-07-05T11:01:06.137311+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/NBYYI5475C5HD35HZTCUKKUGJ4","json":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4.json","graph_json":"https://pith.science/api/pith-number/NBYYI5475C5HD35HZTCUKKUGJ4/graph.json","events_json":"https://pith.science/api/pith-number/NBYYI5475C5HD35HZTCUKKUGJ4/events.json","paper":"https://pith.science/paper/NBYYI547"},"agent_actions":{"view_html":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4","download_json":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4.json","view_paper":"https://pith.science/paper/NBYYI547","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06258&json=true","fetch_graph":"https://pith.science/api/pith-number/NBYYI5475C5HD35HZTCUKKUGJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/NBYYI5475C5HD35HZTCUKKUGJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4/action/storage_attestation","attest_author":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4/action/author_attestation","sign_citation":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4/action/citation_signature","submit_replication":"https://pith.science/pith/NBYYI5475C5HD35HZTCUKKUGJ4/action/replication_record"}},"created_at":"2026-07-05T11:01:06.137311+00:00","updated_at":"2026-07-05T11:01:06.137311+00:00"}