{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RAGNCFNPY5BSNRUKFXZMCOJZRS","short_pith_number":"pith:RAGNCFNP","schema_version":"1.0","canonical_sha256":"880cd115afc74326c68a2df2c139398c8a1e1a2d95a902e106c69f94942bcf72","source":{"kind":"arxiv","id":"2501.01311","version":2},"attestation_state":"computed","paper":{"title":"Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohang Sun, Pietro Li\\`o","submitted_at":"2025-01-02T15:47:56Z","abstract_excerpt":"In this study, we introduce the Multi-Head Explainer (MHEX), a versatile and modular framework that enhances both the explainability and accuracy of Convolutional Neural Networks (CNNs) and Transformer-based models. MHEX consists of three core components: an Attention Gate that dynamically highlights task-relevant features, Deep Supervision that guides early layers to capture fine-grained details pertinent to the target class, and an Equivalent Matrix that unifies refined local and global representations to generate comprehensive saliency maps. Our approach demonstrates superior compatibility,"},"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":"2501.01311","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T15:47:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25de5f2566776c69708d2fd005ff6b80934ae0e0c105c855dec632336237cfed","abstract_canon_sha256":"c9f53832549aa314cd4751f6935c9615fb7e60c306f08cccdf360c9ad18db4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:58.353330Z","signature_b64":"4jTHqtDFm2XM9lpmlh5h+11L0PdaBtvGPqZ5NsNR6qDgY+k9uuApHZWdw9FcnN+zZVYGzSl2w403oNsTTiOnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880cd115afc74326c68a2df2c139398c8a1e1a2d95a902e106c69f94942bcf72","last_reissued_at":"2026-07-05T09:59:58.352893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:58.352893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohang Sun, Pietro Li\\`o","submitted_at":"2025-01-02T15:47:56Z","abstract_excerpt":"In this study, we introduce the Multi-Head Explainer (MHEX), a versatile and modular framework that enhances both the explainability and accuracy of Convolutional Neural Networks (CNNs) and Transformer-based models. MHEX consists of three core components: an Attention Gate that dynamically highlights task-relevant features, Deep Supervision that guides early layers to capture fine-grained details pertinent to the target class, and an Equivalent Matrix that unifies refined local and global representations to generate comprehensive saliency maps. Our approach demonstrates superior compatibility,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01311","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/2501.01311/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":"2501.01311","created_at":"2026-07-05T09:59:58.352942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01311v2","created_at":"2026-07-05T09:59:58.352942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01311","created_at":"2026-07-05T09:59:58.352942+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAGNCFNPY5BS","created_at":"2026-07-05T09:59:58.352942+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAGNCFNPY5BSNRUK","created_at":"2026-07-05T09:59:58.352942+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAGNCFNP","created_at":"2026-07-05T09:59:58.352942+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/RAGNCFNPY5BSNRUKFXZMCOJZRS","json":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS.json","graph_json":"https://pith.science/api/pith-number/RAGNCFNPY5BSNRUKFXZMCOJZRS/graph.json","events_json":"https://pith.science/api/pith-number/RAGNCFNPY5BSNRUKFXZMCOJZRS/events.json","paper":"https://pith.science/paper/RAGNCFNP"},"agent_actions":{"view_html":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS","download_json":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS.json","view_paper":"https://pith.science/paper/RAGNCFNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01311&json=true","fetch_graph":"https://pith.science/api/pith-number/RAGNCFNPY5BSNRUKFXZMCOJZRS/graph.json","fetch_events":"https://pith.science/api/pith-number/RAGNCFNPY5BSNRUKFXZMCOJZRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS/action/storage_attestation","attest_author":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS/action/author_attestation","sign_citation":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS/action/citation_signature","submit_replication":"https://pith.science/pith/RAGNCFNPY5BSNRUKFXZMCOJZRS/action/replication_record"}},"created_at":"2026-07-05T09:59:58.352942+00:00","updated_at":"2026-07-05T09:59:58.352942+00:00"}