{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ORUMHA3POADBAHCUMYNWZ3N6EA","short_pith_number":"pith:ORUMHA3P","schema_version":"1.0","canonical_sha256":"7468c3836f7006101c54661b6cedbe20228d5e7d5413fbc636b3b0bf2c9b0350","source":{"kind":"arxiv","id":"1907.05664","version":1},"attestation_state":"computed","paper":{"title":"Saliency Maps Generation for Automatic Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alessandra Russo, David Tuckey, Krysia Broda","submitted_at":"2019-07-12T10:28:00Z","abstract_excerpt":"Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications. Our goal is to question the limits of these approaches on more complex tasks. In this paper we apply Layer-Wise Relevance Propagation (LRP) to a sequence-to-sequence attention model trained on a text summarization dataset. We obtain unexpected saliency maps and discuss the rightfulness of these \"explanations\". We argue that we need a quantitative way of testing the counterfactual case to judge the truthfulness of the saliency maps. We suggest a protocol to ch"},"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":"1907.05664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-12T10:28:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1efcdd6acdf947d51ce1ccc693b8ae4ca1919df91a377cbf809c3c428b582593","abstract_canon_sha256":"f29c7b11b7fcfc0db6705e97ce0efa3e28e1a9ddc8ec3fc831fe53a3418fe8fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:47.395086Z","signature_b64":"0SV30p/DAp6mgG4ZxgM+mDHrNPz8tnO2Ig7KuY6BfnxjPpgMdyvx2PvdNO1L0L9w12Set8KxO3jBcBSNdTWjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7468c3836f7006101c54661b6cedbe20228d5e7d5413fbc636b3b0bf2c9b0350","last_reissued_at":"2026-05-17T23:40:47.394575Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:47.394575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Saliency Maps Generation for Automatic Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alessandra Russo, David Tuckey, Krysia Broda","submitted_at":"2019-07-12T10:28:00Z","abstract_excerpt":"Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications. Our goal is to question the limits of these approaches on more complex tasks. In this paper we apply Layer-Wise Relevance Propagation (LRP) to a sequence-to-sequence attention model trained on a text summarization dataset. We obtain unexpected saliency maps and discuss the rightfulness of these \"explanations\". We argue that we need a quantitative way of testing the counterfactual case to judge the truthfulness of the saliency maps. We suggest a protocol to ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05664","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":"1907.05664","created_at":"2026-05-17T23:40:47.394661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05664v1","created_at":"2026-05-17T23:40:47.394661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05664","created_at":"2026-05-17T23:40:47.394661+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORUMHA3POADB","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORUMHA3POADBAHCU","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORUMHA3P","created_at":"2026-05-18T12:33:24.271573+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/ORUMHA3POADBAHCUMYNWZ3N6EA","json":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA.json","graph_json":"https://pith.science/api/pith-number/ORUMHA3POADBAHCUMYNWZ3N6EA/graph.json","events_json":"https://pith.science/api/pith-number/ORUMHA3POADBAHCUMYNWZ3N6EA/events.json","paper":"https://pith.science/paper/ORUMHA3P"},"agent_actions":{"view_html":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA","download_json":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA.json","view_paper":"https://pith.science/paper/ORUMHA3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05664&json=true","fetch_graph":"https://pith.science/api/pith-number/ORUMHA3POADBAHCUMYNWZ3N6EA/graph.json","fetch_events":"https://pith.science/api/pith-number/ORUMHA3POADBAHCUMYNWZ3N6EA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA/action/storage_attestation","attest_author":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA/action/author_attestation","sign_citation":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA/action/citation_signature","submit_replication":"https://pith.science/pith/ORUMHA3POADBAHCUMYNWZ3N6EA/action/replication_record"}},"created_at":"2026-05-17T23:40:47.394661+00:00","updated_at":"2026-05-17T23:40:47.394661+00:00"}