{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ST33XUKBFRGKWJSPTC66EGJ4QQ","short_pith_number":"pith:ST33XUKB","schema_version":"1.0","canonical_sha256":"94f7bbd1412c4cab264f98bde2193c8413ac6f469787341f186505a61313a74a","source":{"kind":"arxiv","id":"1808.02113","version":1},"attestation_state":"computed","paper":{"title":"Paying Attention to Attention: Highlighting Influential Samples in Sequential Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdullah Mueen, Abhinav Aggarwal, Cynthia Freeman, Ian Beaver, Jonathan Merriman","submitted_at":"2018-08-06T21:05:55Z","abstract_excerpt":"In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying the document, thereby explaining the model's prediction. We successfully applied HAN to a sequential analysis task in the form of real-time monitoring of turn taking in conversations. However, we discovered instances where the attention weights were uniform at the stopping point (indicating all turns were equivalently influential to the classifier), preventing meaningful visualization for real-time human review or cla"},"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":"1808.02113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-06T21:05:55Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"7d70f632b409c7825a58337a1eec9f3dadcb25069c82f0ccaaa1e9faa2826e75","abstract_canon_sha256":"105b1195b37828b8c4be953901780d61f4a7ba1b9d12493356bdd68a40233e8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:47.582279Z","signature_b64":"TC7IkhPsJotfPtgIRK4VJ3ZXaMEAZV33owwp/xYu5b1sEGDSXXgkNfEBOy47SB5VNeEsFFbXmECbWQnI4xnnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f7bbd1412c4cab264f98bde2193c8413ac6f469787341f186505a61313a74a","last_reissued_at":"2026-05-18T00:08:47.581730Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:47.581730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Paying Attention to Attention: Highlighting Influential Samples in Sequential Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdullah Mueen, Abhinav Aggarwal, Cynthia Freeman, Ian Beaver, Jonathan Merriman","submitted_at":"2018-08-06T21:05:55Z","abstract_excerpt":"In (Yang et al. 2016), a hierarchical attention network (HAN) is created for document classification. The attention layer can be used to visualize text influential in classifying the document, thereby explaining the model's prediction. We successfully applied HAN to a sequential analysis task in the form of real-time monitoring of turn taking in conversations. However, we discovered instances where the attention weights were uniform at the stopping point (indicating all turns were equivalently influential to the classifier), preventing meaningful visualization for real-time human review or cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02113","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":""},"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":"1808.02113","created_at":"2026-05-18T00:08:47.581804+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02113v1","created_at":"2026-05-18T00:08:47.581804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02113","created_at":"2026-05-18T00:08:47.581804+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST33XUKBFRGK","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST33XUKBFRGKWJSP","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST33XUKB","created_at":"2026-05-18T12:32:53.628368+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/ST33XUKBFRGKWJSPTC66EGJ4QQ","json":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ.json","graph_json":"https://pith.science/api/pith-number/ST33XUKBFRGKWJSPTC66EGJ4QQ/graph.json","events_json":"https://pith.science/api/pith-number/ST33XUKBFRGKWJSPTC66EGJ4QQ/events.json","paper":"https://pith.science/paper/ST33XUKB"},"agent_actions":{"view_html":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ","download_json":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ.json","view_paper":"https://pith.science/paper/ST33XUKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02113&json=true","fetch_graph":"https://pith.science/api/pith-number/ST33XUKBFRGKWJSPTC66EGJ4QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ST33XUKBFRGKWJSPTC66EGJ4QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ/action/storage_attestation","attest_author":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ/action/author_attestation","sign_citation":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ/action/citation_signature","submit_replication":"https://pith.science/pith/ST33XUKBFRGKWJSPTC66EGJ4QQ/action/replication_record"}},"created_at":"2026-05-18T00:08:47.581804+00:00","updated_at":"2026-05-18T00:08:47.581804+00:00"}