{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BBO3BSTEWZW2WP5OCOUJNJ37XK","short_pith_number":"pith:BBO3BSTE","schema_version":"1.0","canonical_sha256":"085db0ca64b66dab3fae13a896a77fba9eb7c1e1100dff9eb04d8ff6080a477a","source":{"kind":"arxiv","id":"1802.04712","version":4},"attestation_state":"computed","paper":{"title":"Attention-based Deep Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Maximilian Ilse, Max Welling","submitted_at":"2018-02-13T16:27:19Z","abstract_excerpt":"Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we propose a neural network-based permutation-invariant aggregation operator that corresponds to the attention mechanism. Notably, an application of the proposed attention-based operator provides insight into the contribution of each instance to the bag label. We show empirically th"},"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":"1802.04712","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T16:27:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6afd9e765cf2a996c7762c9d3e61a86448dd4d726b038000d99e96138614cbf4","abstract_canon_sha256":"7bd2606b7e6cf65eec0855ecb8727f949f27959a0f33b143425e4a2c174c0f16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:08.917799Z","signature_b64":"beCor27Vq5E4XjAf5LMBYRBhQlvdrUbydJ0Cknrv5ZfZkOrh2DowEg5D4hIRdqcYt1rRUobmGuPX99x/j7bLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085db0ca64b66dab3fae13a896a77fba9eb7c1e1100dff9eb04d8ff6080a477a","last_reissued_at":"2026-05-18T00:12:08.917042Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:08.917042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-based Deep Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Maximilian Ilse, Max Welling","submitted_at":"2018-02-13T16:27:19Z","abstract_excerpt":"Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we propose a neural network-based permutation-invariant aggregation operator that corresponds to the attention mechanism. Notably, an application of the proposed attention-based operator provides insight into the contribution of each instance to the bag label. We show empirically th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04712","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.04712","created_at":"2026-05-18T00:12:08.917154+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04712v4","created_at":"2026-05-18T00:12:08.917154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04712","created_at":"2026-05-18T00:12:08.917154+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBO3BSTEWZW2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBO3BSTEWZW2WP5O","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBO3BSTE","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.01734","citing_title":"AMI-Net+: A Novel Multi-Instance Neural Network for Medical Diagnosis from Incomplete and Imbalanced Data","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05126","citing_title":"CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05126","citing_title":"CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22347","citing_title":"Enabling clinical use of foundation models for computational pathology","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23706","citing_title":"Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08197","citing_title":"Discrete Diffusion for Codebook-Based Beam Candidate Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15096","citing_title":"Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02614","citing_title":"Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK","json":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK.json","graph_json":"https://pith.science/api/pith-number/BBO3BSTEWZW2WP5OCOUJNJ37XK/graph.json","events_json":"https://pith.science/api/pith-number/BBO3BSTEWZW2WP5OCOUJNJ37XK/events.json","paper":"https://pith.science/paper/BBO3BSTE"},"agent_actions":{"view_html":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK","download_json":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK.json","view_paper":"https://pith.science/paper/BBO3BSTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04712&json=true","fetch_graph":"https://pith.science/api/pith-number/BBO3BSTEWZW2WP5OCOUJNJ37XK/graph.json","fetch_events":"https://pith.science/api/pith-number/BBO3BSTEWZW2WP5OCOUJNJ37XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK/action/storage_attestation","attest_author":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK/action/author_attestation","sign_citation":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK/action/citation_signature","submit_replication":"https://pith.science/pith/BBO3BSTEWZW2WP5OCOUJNJ37XK/action/replication_record"}},"created_at":"2026-05-18T00:12:08.917154+00:00","updated_at":"2026-05-18T00:12:08.917154+00:00"}