{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NNCPELOLE6PRW26LZVDZQLHGXV","short_pith_number":"pith:NNCPELOL","schema_version":"1.0","canonical_sha256":"6b44f22dcb279f1b6bcbcd47982ce6bd78ed3b911cc5ed1a213de802db64e2f6","source":{"kind":"arxiv","id":"2606.20027","version":1},"attestation_state":"computed","paper":{"title":"QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Loddo, Carsten Marr, Cecilia Di Ruberto, Davide Antonio Mura, Luca Zedda, Maurizio Atzori, Muhammed Furkan Dasdelen","submitted_at":"2026-06-18T09:58:50Z","abstract_excerpt":"Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MIL, a gated transformer aggregator that addresses this through four synergistic architectural components: RMSNorm-based pre-normalization, per-head QK normalization, fine-grained attention output gating, and SwiGLU-style feed-forward modules. Together, these design choices stabilize training and distribute attention more uniformly across instances without auxiliary losses, masking, or multi-stage regularization. We ev"},"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":"2606.20027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:58:50Z","cross_cats_sorted":[],"title_canon_sha256":"80858aa32d8b16ee5c10d74112b9b933121130c4edf84ab893249f0454783d89","abstract_canon_sha256":"7392bfd7c6a9f31843ebbe85ecbdc8650fbfebdfbe1d8db80cc231b1651fc86f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:01.068336Z","signature_b64":"XzKCNwK3tEXvgbP8JQhHdwBaU0u9yUxV/TitMUjmur6cvCjAxlDyKcmy7c2Xij9n9XHekGkukinR+zgvcpUPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b44f22dcb279f1b6bcbcd47982ce6bd78ed3b911cc5ed1a213de802db64e2f6","last_reissued_at":"2026-06-19T16:13:01.067973Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:01.067973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Loddo, Carsten Marr, Cecilia Di Ruberto, Davide Antonio Mura, Luca Zedda, Maurizio Atzori, Muhammed Furkan Dasdelen","submitted_at":"2026-06-18T09:58:50Z","abstract_excerpt":"Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MIL, a gated transformer aggregator that addresses this through four synergistic architectural components: RMSNorm-based pre-normalization, per-head QK normalization, fine-grained attention output gating, and SwiGLU-style feed-forward modules. Together, these design choices stabilize training and distribute attention more uniformly across instances without auxiliary losses, masking, or multi-stage regularization. We ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20027","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/2606.20027/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":"2606.20027","created_at":"2026-06-19T16:13:01.068037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20027v1","created_at":"2026-06-19T16:13:01.068037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20027","created_at":"2026-06-19T16:13:01.068037+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNCPELOLE6PR","created_at":"2026-06-19T16:13:01.068037+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNCPELOLE6PRW26L","created_at":"2026-06-19T16:13:01.068037+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNCPELOL","created_at":"2026-06-19T16:13:01.068037+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/NNCPELOLE6PRW26LZVDZQLHGXV","json":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV.json","graph_json":"https://pith.science/api/pith-number/NNCPELOLE6PRW26LZVDZQLHGXV/graph.json","events_json":"https://pith.science/api/pith-number/NNCPELOLE6PRW26LZVDZQLHGXV/events.json","paper":"https://pith.science/paper/NNCPELOL"},"agent_actions":{"view_html":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV","download_json":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV.json","view_paper":"https://pith.science/paper/NNCPELOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20027&json=true","fetch_graph":"https://pith.science/api/pith-number/NNCPELOLE6PRW26LZVDZQLHGXV/graph.json","fetch_events":"https://pith.science/api/pith-number/NNCPELOLE6PRW26LZVDZQLHGXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV/action/storage_attestation","attest_author":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV/action/author_attestation","sign_citation":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV/action/citation_signature","submit_replication":"https://pith.science/pith/NNCPELOLE6PRW26LZVDZQLHGXV/action/replication_record"}},"created_at":"2026-06-19T16:13:01.068037+00:00","updated_at":"2026-06-19T16:13:01.068037+00:00"}