{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7XYFNOEXDCGJLXA763354WI2Q4","short_pith_number":"pith:7XYFNOEX","schema_version":"1.0","canonical_sha256":"fdf056b897188c95dc1ff6f7de591a8719ec1b73b39dc29467ea2f0aded934a5","source":{"kind":"arxiv","id":"1810.02938","version":1},"attestation_state":"computed","paper":{"title":"Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Luu Anh Tuan, Siu Cheung Hui, Yi Tay","submitted_at":"2018-10-06T05:25:24Z","abstract_excerpt":"Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two n"},"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":"1810.02938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-06T05:25:24Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"4aad6214b54184e04f1a6de523beca47ea6de79874ce13c267917cd6488f3d87","abstract_canon_sha256":"61e1f74249980a2bc741e4a9293a0772384bf6088823d27f69c1e0807f731933"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:55.083331Z","signature_b64":"xV15YH10kMKhNfVfPBfSFzTova15zsaIVKHNHcPtGCxM8neSi/KIaLnaePJ4t3HlNX/C7RB0dOwE3yIbn+36Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf056b897188c95dc1ff6f7de591a8719ec1b73b39dc29467ea2f0aded934a5","last_reissued_at":"2026-05-18T00:03:55.082821Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:55.082821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Luu Anh Tuan, Siu Cheung Hui, Yi Tay","submitted_at":"2018-10-06T05:25:24Z","abstract_excerpt":"Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02938","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":"1810.02938","created_at":"2026-05-18T00:03:55.082900+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02938v1","created_at":"2026-05-18T00:03:55.082900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02938","created_at":"2026-05-18T00:03:55.082900+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XYFNOEXDCGJ","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XYFNOEXDCGJLXA7","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XYFNOEX","created_at":"2026-05-18T12:32:11.075285+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/7XYFNOEXDCGJLXA763354WI2Q4","json":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4.json","graph_json":"https://pith.science/api/pith-number/7XYFNOEXDCGJLXA763354WI2Q4/graph.json","events_json":"https://pith.science/api/pith-number/7XYFNOEXDCGJLXA763354WI2Q4/events.json","paper":"https://pith.science/paper/7XYFNOEX"},"agent_actions":{"view_html":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4","download_json":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4.json","view_paper":"https://pith.science/paper/7XYFNOEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02938&json=true","fetch_graph":"https://pith.science/api/pith-number/7XYFNOEXDCGJLXA763354WI2Q4/graph.json","fetch_events":"https://pith.science/api/pith-number/7XYFNOEXDCGJLXA763354WI2Q4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4/action/storage_attestation","attest_author":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4/action/author_attestation","sign_citation":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4/action/citation_signature","submit_replication":"https://pith.science/pith/7XYFNOEXDCGJLXA763354WI2Q4/action/replication_record"}},"created_at":"2026-05-18T00:03:55.082900+00:00","updated_at":"2026-05-18T00:03:55.082900+00:00"}