{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D26XSMHJD4CPZK4LBRWTTD7YEN","short_pith_number":"pith:D26XSMHJ","schema_version":"1.0","canonical_sha256":"1ebd7930e91f04fcab8b0c6d398ff8235688fd6ceb45d3898f84b5736d511bc0","source":{"kind":"arxiv","id":"1606.05554","version":1},"attestation_state":"computed","paper":{"title":"SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"A. Stephen McGough, Noura Al Moubayed, Peter Matthews, Toby Breckon","submitted_at":"2016-06-17T15:15:18Z","abstract_excerpt":"In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages. Our approach requires minimum features engineering and a small set of la- belled data samples. Features are extracted using topic modelling based on latent Dirichlet allocation, and then a comprehensive data model is created using a Stacked Denoising Autoencoder (SDA). Topic modelling summarises the data providing ease of use and high interpretability by visualising the topics using word clouds. Given that the SMS messages can be regarded as either spam (unwanted) or ham "},"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":"1606.05554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-17T15:15:18Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"c5e54a3ea03e10298d3ca80675e17229ad0d3e7c2e6f48862505e4c43c6e1d05","abstract_canon_sha256":"69fde04c08bfd7f3e843d180d2f4f23e62c0d53df73f32b022483e7047f11167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:19.422155Z","signature_b64":"mBAWFG65muljfU+0zZ69v3TCz1ghnYWv/Xq0DWGQ1KPPkiUw1v7SviRVOydayu9RXxpAhr7xMTyEos6mLdhUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebd7930e91f04fcab8b0c6d398ff8235688fd6ceb45d3898f84b5736d511bc0","last_reissued_at":"2026-05-18T01:12:19.421784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:19.421784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"A. Stephen McGough, Noura Al Moubayed, Peter Matthews, Toby Breckon","submitted_at":"2016-06-17T15:15:18Z","abstract_excerpt":"In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages. Our approach requires minimum features engineering and a small set of la- belled data samples. Features are extracted using topic modelling based on latent Dirichlet allocation, and then a comprehensive data model is created using a Stacked Denoising Autoencoder (SDA). Topic modelling summarises the data providing ease of use and high interpretability by visualising the topics using word clouds. Given that the SMS messages can be regarded as either spam (unwanted) or ham "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05554","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":"1606.05554","created_at":"2026-05-18T01:12:19.421839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05554v1","created_at":"2026-05-18T01:12:19.421839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05554","created_at":"2026-05-18T01:12:19.421839+00:00"},{"alias_kind":"pith_short_12","alias_value":"D26XSMHJD4CP","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D26XSMHJD4CPZK4L","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D26XSMHJ","created_at":"2026-05-18T12:30:09.641336+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/D26XSMHJD4CPZK4LBRWTTD7YEN","json":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN.json","graph_json":"https://pith.science/api/pith-number/D26XSMHJD4CPZK4LBRWTTD7YEN/graph.json","events_json":"https://pith.science/api/pith-number/D26XSMHJD4CPZK4LBRWTTD7YEN/events.json","paper":"https://pith.science/paper/D26XSMHJ"},"agent_actions":{"view_html":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN","download_json":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN.json","view_paper":"https://pith.science/paper/D26XSMHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05554&json=true","fetch_graph":"https://pith.science/api/pith-number/D26XSMHJD4CPZK4LBRWTTD7YEN/graph.json","fetch_events":"https://pith.science/api/pith-number/D26XSMHJD4CPZK4LBRWTTD7YEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN/action/storage_attestation","attest_author":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN/action/author_attestation","sign_citation":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN/action/citation_signature","submit_replication":"https://pith.science/pith/D26XSMHJD4CPZK4LBRWTTD7YEN/action/replication_record"}},"created_at":"2026-05-18T01:12:19.421839+00:00","updated_at":"2026-05-18T01:12:19.421839+00:00"}