{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7M6OENMC6G2LKVTVPPKFDICVZK","short_pith_number":"pith:7M6OENMC","canonical_record":{"source":{"id":"1912.00315","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-01T04:22:51Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"29f7ec4c5ae6ab4466d299e939ba9da0cfbd5025f2f8ef448984564609132726","abstract_canon_sha256":"02dbef79525ceb030b4084dd78990327a667f02a0045fc40b4cf078c13f1322c"},"schema_version":"1.0"},"canonical_sha256":"fb3ce23582f1b4b556757bd451a055ca9bd237c83c2a0abb24f1b10fd9817e05","source":{"kind":"arxiv","id":"1912.00315","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00315","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00315v2","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00315","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"7M6OENMC6G2L","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"7M6OENMC6G2LKVTV","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"7M6OENMC","created_at":"2026-07-05T00:23:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7M6OENMC6G2LKVTVPPKFDICVZK","target":"record","payload":{"canonical_record":{"source":{"id":"1912.00315","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-01T04:22:51Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"29f7ec4c5ae6ab4466d299e939ba9da0cfbd5025f2f8ef448984564609132726","abstract_canon_sha256":"02dbef79525ceb030b4084dd78990327a667f02a0045fc40b4cf078c13f1322c"},"schema_version":"1.0"},"canonical_sha256":"fb3ce23582f1b4b556757bd451a055ca9bd237c83c2a0abb24f1b10fd9817e05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:52.335357Z","signature_b64":"wjKmTJwHF66OK4q3qn2hvLeBagvGuQ5CG9TbRzz/c3AQMu6iKhJsGLALUigmgX+JbTsBkpP6SPI+nQNpraoZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb3ce23582f1b4b556757bd451a055ca9bd237c83c2a0abb24f1b10fd9817e05","last_reissued_at":"2026-07-05T00:23:52.334908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:52.334908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.00315","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNSRgAjmAFRygqpabyEKVOFM4i+yGOmx6QD6i9i6x+uQYabpyj2YoM59MoZa6kDIeBOvUXP7ZJTK3MjFd2vzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T03:15:14.368309Z"},"content_sha256":"a2c7498a127b70964735a47cf0552b775531aca13d9b537c23444bd49f78a653","schema_version":"1.0","event_id":"sha256:a2c7498a127b70964735a47cf0552b775531aca13d9b537c23444bd49f78a653"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7M6OENMC6G2LKVTVPPKFDICVZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.CL","authors_text":"Deanna Needell, Hanbaek Lyu, Henry Sojico, Jiahao Qu, Nicholas Hanoian, Nicholas Liskij, Yuchen Guo, Yuliang Wang, Zhenhong Zou, Zhexiao Lin, Zhe Xiong","submitted_at":"2019-12-01T04:22:51Z","abstract_excerpt":"We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF). After learning topic vectors from an auxiliary text corpus via NMF, the decoder is trained so that it is more likely to sample response words from the most correlated topic vectors. One of the main advantages in our architecture is that the user can easily switch the NMF-learned topic vectors so that the chatbot obtains desired topic-awareness. We demonstrate our model by training on a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00315","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.00315/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xVAR21hQ17XgkU6lIEUf2k4qbWG5vIkVsSM2XzNPZg5Vdbt5CaAj1EM4/poC8TBnyTcsj0nU2nNc3GDbwlFwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T03:15:14.368708Z"},"content_sha256":"6276f5c4e7281f590faa824935fc2d9f5c513a7b720d4b1992f5f7736cebc42a","schema_version":"1.0","event_id":"sha256:6276f5c4e7281f590faa824935fc2d9f5c513a7b720d4b1992f5f7736cebc42a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7M6OENMC6G2LKVTVPPKFDICVZK/bundle.json","state_url":"https://pith.science/pith/7M6OENMC6G2LKVTVPPKFDICVZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7M6OENMC6G2LKVTVPPKFDICVZK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-21T03:15:14Z","links":{"resolver":"https://pith.science/pith/7M6OENMC6G2LKVTVPPKFDICVZK","bundle":"https://pith.science/pith/7M6OENMC6G2LKVTVPPKFDICVZK/bundle.json","state":"https://pith.science/pith/7M6OENMC6G2LKVTVPPKFDICVZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7M6OENMC6G2LKVTVPPKFDICVZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7M6OENMC6G2LKVTVPPKFDICVZK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"02dbef79525ceb030b4084dd78990327a667f02a0045fc40b4cf078c13f1322c","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-01T04:22:51Z","title_canon_sha256":"29f7ec4c5ae6ab4466d299e939ba9da0cfbd5025f2f8ef448984564609132726"},"schema_version":"1.0","source":{"id":"1912.00315","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00315","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00315v2","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00315","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"7M6OENMC6G2L","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"7M6OENMC6G2LKVTV","created_at":"2026-07-05T00:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"7M6OENMC","created_at":"2026-07-05T00:23:52Z"}],"graph_snapshots":[{"event_id":"sha256:6276f5c4e7281f590faa824935fc2d9f5c513a7b720d4b1992f5f7736cebc42a","target":"graph","created_at":"2026-07-05T00:23:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1912.00315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF). After learning topic vectors from an auxiliary text corpus via NMF, the decoder is trained so that it is more likely to sample response words from the most correlated topic vectors. One of the main advantages in our architecture is that the user can easily switch the NMF-learned topic vectors so that the chatbot obtains desired topic-awareness. We demonstrate our model by training on a ","authors_text":"Deanna Needell, Hanbaek Lyu, Henry Sojico, Jiahao Qu, Nicholas Hanoian, Nicholas Liskij, Yuchen Guo, Yuliang Wang, Zhenhong Zou, Zhexiao Lin, Zhe Xiong","cross_cats":["cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-01T04:22:51Z","title":"Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00315","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a2c7498a127b70964735a47cf0552b775531aca13d9b537c23444bd49f78a653","target":"record","created_at":"2026-07-05T00:23:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"02dbef79525ceb030b4084dd78990327a667f02a0045fc40b4cf078c13f1322c","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-01T04:22:51Z","title_canon_sha256":"29f7ec4c5ae6ab4466d299e939ba9da0cfbd5025f2f8ef448984564609132726"},"schema_version":"1.0","source":{"id":"1912.00315","kind":"arxiv","version":2}},"canonical_sha256":"fb3ce23582f1b4b556757bd451a055ca9bd237c83c2a0abb24f1b10fd9817e05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb3ce23582f1b4b556757bd451a055ca9bd237c83c2a0abb24f1b10fd9817e05","first_computed_at":"2026-07-05T00:23:52.334908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:52.334908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wjKmTJwHF66OK4q3qn2hvLeBagvGuQ5CG9TbRzz/c3AQMu6iKhJsGLALUigmgX+JbTsBkpP6SPI+nQNpraoZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:52.335357Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00315","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2c7498a127b70964735a47cf0552b775531aca13d9b537c23444bd49f78a653","sha256:6276f5c4e7281f590faa824935fc2d9f5c513a7b720d4b1992f5f7736cebc42a"],"state_sha256":"9aa38760db2a9caea6c6806a7f917e32eddafe6078dd09e68b769089ca1ac1c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sK1jBj1C6pzahsLNnFy611RAPX1Xfv6jZCrr80AXXuk+8K13K9UzQNXg0/9DkD3vwV0dy6DC9Nbh08DCGqvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T03:15:14.371207Z","bundle_sha256":"fac047ad5a62a9ddb61451891585b6a398c15556e8c694570283cb1f0554f6b2"}}