{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:K6HJTHQOS6UIVJZXA5WYNM5KZI","short_pith_number":"pith:K6HJTHQO","schema_version":"1.0","canonical_sha256":"578e999e0e97a88aa737076d86b3aaca2d3432f1428e23a572ab69a136941f6c","source":{"kind":"arxiv","id":"1612.01627","version":2},"attestation_state":"computed","paper":{"title":"Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Xing, Ming Zhou, Wei Wu, Yu Wu, Zhoujun Li","submitted_at":"2016-12-06T01:57:39Z","abstract_excerpt":"We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information. We propose a sequential matching network (SMN) to address both problems. SMN first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then ac"},"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":"1612.01627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-06T01:57:39Z","cross_cats_sorted":[],"title_canon_sha256":"148e1504815a00821adf0a5179875b461aab0d1db282987ee65c917364e1231c","abstract_canon_sha256":"d4a2d4478c050e05125b74038d4540a7235c91a8b36d263606aab87aa456d7fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:33.578269Z","signature_b64":"1HeBOdgni3sQ91MIVHKuYCPwoUXsZ42SkpnpRtNtgn9B/LpTxzAPmyOMtKBRlOZ4JOf0IbLLfxyuAiZw8JO3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"578e999e0e97a88aa737076d86b3aaca2d3432f1428e23a572ab69a136941f6c","last_reissued_at":"2026-05-18T00:44:33.577758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:33.577758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Xing, Ming Zhou, Wei Wu, Yu Wu, Zhoujun Li","submitted_at":"2016-12-06T01:57:39Z","abstract_excerpt":"We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information. We propose a sequential matching network (SMN) to address both problems. SMN first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01627","kind":"arxiv","version":2},"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":"1612.01627","created_at":"2026-05-18T00:44:33.577852+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.01627v2","created_at":"2026-05-18T00:44:33.577852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01627","created_at":"2026-05-18T00:44:33.577852+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6HJTHQOS6UI","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6HJTHQOS6UIVJZX","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6HJTHQO","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05792","citing_title":"Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI","json":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI.json","graph_json":"https://pith.science/api/pith-number/K6HJTHQOS6UIVJZXA5WYNM5KZI/graph.json","events_json":"https://pith.science/api/pith-number/K6HJTHQOS6UIVJZXA5WYNM5KZI/events.json","paper":"https://pith.science/paper/K6HJTHQO"},"agent_actions":{"view_html":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI","download_json":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI.json","view_paper":"https://pith.science/paper/K6HJTHQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.01627&json=true","fetch_graph":"https://pith.science/api/pith-number/K6HJTHQOS6UIVJZXA5WYNM5KZI/graph.json","fetch_events":"https://pith.science/api/pith-number/K6HJTHQOS6UIVJZXA5WYNM5KZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI/action/storage_attestation","attest_author":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI/action/author_attestation","sign_citation":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI/action/citation_signature","submit_replication":"https://pith.science/pith/K6HJTHQOS6UIVJZXA5WYNM5KZI/action/replication_record"}},"created_at":"2026-05-18T00:44:33.577852+00:00","updated_at":"2026-05-18T00:44:33.577852+00:00"}