{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LYCJNP7CW3N2EDWT53WBWBDL44","short_pith_number":"pith:LYCJNP7C","schema_version":"1.0","canonical_sha256":"5e0496bfe2b6dba20ed3eeec1b046be71a9c1cc5c427c50a2113fa2f52d2adc5","source":{"kind":"arxiv","id":"1805.09653","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Attention for Reliable Interpretation and Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eunho Yang, Hae Beom Lee, Jay Heo, Juho Lee, Kwang Joon Kim, Saehoon Kim, Sung Ju Hwang","submitted_at":"2018-05-24T13:17:08Z","abstract_excerpt":"Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent uncertainty to the attention mechanism, such that it generates attention for each feature with varying degrees of noise based on the given input, to learn larger variance on instances it is uncertain about. We learn this Uncertainty-aware Attention (UA) mechanism using variational 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":"1805.09653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T13:17:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"582c01f803db718fb6f9c8049c7b073a6d7ff654d644dff9b34303aa6ed71caa","abstract_canon_sha256":"d219bb6f966a90b46bc8e54f880c992569420905750e2f3033245cbecd5f1e37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:57.916039Z","signature_b64":"QbFixghdhGwtfnkFQT/ASWatGCJj4lbDvh1jpjwsylD7PJEfzpi5QRJEWZ+eSFwyZ3DOxxIjq9nbER9sXeT5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e0496bfe2b6dba20ed3eeec1b046be71a9c1cc5c427c50a2113fa2f52d2adc5","last_reissued_at":"2026-07-05T01:08:57.915615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:57.915615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Attention for Reliable Interpretation and Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eunho Yang, Hae Beom Lee, Jay Heo, Juho Lee, Kwang Joon Kim, Saehoon Kim, Sung Ju Hwang","submitted_at":"2018-05-24T13:17:08Z","abstract_excerpt":"Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent uncertainty to the attention mechanism, such that it generates attention for each feature with varying degrees of noise based on the given input, to learn larger variance on instances it is uncertain about. We learn this Uncertainty-aware Attention (UA) mechanism using variational in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09653","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/1805.09653/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":"1805.09653","created_at":"2026-07-05T01:08:57.915672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09653v1","created_at":"2026-07-05T01:08:57.915672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09653","created_at":"2026-07-05T01:08:57.915672+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYCJNP7CW3N2","created_at":"2026-07-05T01:08:57.915672+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYCJNP7CW3N2EDWT","created_at":"2026-07-05T01:08:57.915672+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYCJNP7C","created_at":"2026-07-05T01:08:57.915672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44","json":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44.json","graph_json":"https://pith.science/api/pith-number/LYCJNP7CW3N2EDWT53WBWBDL44/graph.json","events_json":"https://pith.science/api/pith-number/LYCJNP7CW3N2EDWT53WBWBDL44/events.json","paper":"https://pith.science/paper/LYCJNP7C"},"agent_actions":{"view_html":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44","download_json":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44.json","view_paper":"https://pith.science/paper/LYCJNP7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09653&json=true","fetch_graph":"https://pith.science/api/pith-number/LYCJNP7CW3N2EDWT53WBWBDL44/graph.json","fetch_events":"https://pith.science/api/pith-number/LYCJNP7CW3N2EDWT53WBWBDL44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44/action/storage_attestation","attest_author":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44/action/author_attestation","sign_citation":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44/action/citation_signature","submit_replication":"https://pith.science/pith/LYCJNP7CW3N2EDWT53WBWBDL44/action/replication_record"}},"created_at":"2026-07-05T01:08:57.915672+00:00","updated_at":"2026-07-05T01:08:57.915672+00:00"}