{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2YKWAZNX5FXOG2KHDV3Y7CFEN6","short_pith_number":"pith:2YKWAZNX","canonical_record":{"source":{"id":"1702.07117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T07:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"6f13806b0509df6fb2b305b020d1fbf227aade15f35c91bb3998dec196ae0718","abstract_canon_sha256":"07f14611b8f6bf94f5133dc27057eba79f78f915e8d3537ce98669f3439022a0"},"schema_version":"1.0"},"canonical_sha256":"d6156065b7e96ee369471d778f88a46f9fa39b91a0d89b52afd0067389fca782","source":{"kind":"arxiv","id":"1702.07117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07117","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07117v1","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07117","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"pith_short_12","alias_value":"2YKWAZNX5FXO","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YKWAZNX5FXOG2KH","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YKWAZNX","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2YKWAZNX5FXOG2KHDV3Y7CFEN6","target":"record","payload":{"canonical_record":{"source":{"id":"1702.07117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T07:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"6f13806b0509df6fb2b305b020d1fbf227aade15f35c91bb3998dec196ae0718","abstract_canon_sha256":"07f14611b8f6bf94f5133dc27057eba79f78f915e8d3537ce98669f3439022a0"},"schema_version":"1.0"},"canonical_sha256":"d6156065b7e96ee369471d778f88a46f9fa39b91a0d89b52afd0067389fca782","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:08.247014Z","signature_b64":"FjV4tEUN/XQ08ihpRsJlLvcGbdS+U9+8SloZze6Cdw89UFwSzhK2fNiiuTSzsXbdvSpuokp5RvxbE7xpvYgZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6156065b7e96ee369471d778f88a46f9fa39b91a0d89b52afd0067389fca782","last_reissued_at":"2026-05-18T00:50:08.246439Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:08.246439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.07117","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQB75qO6AhweajKpzCgoRppYCeaeGT0pXJgTxMNApy6YWIZF/VIRrGWb5k0I7+04gY6h/naKtGALre0IclxaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:10:42.971704Z"},"content_sha256":"a28f669064a45f6a0edc56f3fb60049a3d023ef07cb65b901e7ecbf4676333f4","schema_version":"1.0","event_id":"sha256:a28f669064a45f6a0edc56f3fb60049a3d023ef07cb65b901e7ecbf4676333f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2YKWAZNX5FXOG2KHDV3Y7CFEN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"China.), Erhu Rong (Dept. of Computer Science, Guangzhou, Hankz Hankui Zhuo, Jarvan Law, Junhua He, Sun Yat-sen University","submitted_at":"2017-02-23T07:16:03Z","abstract_excerpt":"Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value vector space, which have obtained high performance in NLP tasks. However, most of the existing models assume the result trained by one of them are perfect correct and used as prior knowledge for improving the other model. Some other models use the information trained from external large corpus to help improving smaller corpus. In this paper, we aim to build"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07117","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbOIwGS9jbZw8g9zB2slG09v7CgAWdDzsa5vjNB8IP8NGEpLrjqisEqOwlLoQTABU15xEHOK+za+Tg4rrcbEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:10:42.972433Z"},"content_sha256":"d3cc3cdbadb660825d2e7050be5ee5e501dd97f8a390fe406d59398f6e7ae323","schema_version":"1.0","event_id":"sha256:d3cc3cdbadb660825d2e7050be5ee5e501dd97f8a390fe406d59398f6e7ae323"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/bundle.json","state_url":"https://pith.science/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/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":"2026-05-23T13:10:42Z","links":{"resolver":"https://pith.science/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6","bundle":"https://pith.science/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/bundle.json","state":"https://pith.science/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YKWAZNX5FXOG2KHDV3Y7CFEN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2YKWAZNX5FXOG2KHDV3Y7CFEN6","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":"07f14611b8f6bf94f5133dc27057eba79f78f915e8d3537ce98669f3439022a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T07:16:03Z","title_canon_sha256":"6f13806b0509df6fb2b305b020d1fbf227aade15f35c91bb3998dec196ae0718"},"schema_version":"1.0","source":{"id":"1702.07117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07117","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07117v1","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07117","created_at":"2026-05-18T00:50:08Z"},{"alias_kind":"pith_short_12","alias_value":"2YKWAZNX5FXO","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2YKWAZNX5FXOG2KH","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2YKWAZNX","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:d3cc3cdbadb660825d2e7050be5ee5e501dd97f8a390fe406d59398f6e7ae323","target":"graph","created_at":"2026-05-18T00:50:08Z","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"},"paper":{"abstract_excerpt":"Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value vector space, which have obtained high performance in NLP tasks. However, most of the existing models assume the result trained by one of them are perfect correct and used as prior knowledge for improving the other model. Some other models use the information trained from external large corpus to help improving smaller corpus. In this paper, we aim to build","authors_text":"China.), Erhu Rong (Dept. of Computer Science, Guangzhou, Hankz Hankui Zhuo, Jarvan Law, Junhua He, Sun Yat-sen University","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T07:16:03Z","title":"LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07117","kind":"arxiv","version":1},"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:a28f669064a45f6a0edc56f3fb60049a3d023ef07cb65b901e7ecbf4676333f4","target":"record","created_at":"2026-05-18T00:50:08Z","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":"07f14611b8f6bf94f5133dc27057eba79f78f915e8d3537ce98669f3439022a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-23T07:16:03Z","title_canon_sha256":"6f13806b0509df6fb2b305b020d1fbf227aade15f35c91bb3998dec196ae0718"},"schema_version":"1.0","source":{"id":"1702.07117","kind":"arxiv","version":1}},"canonical_sha256":"d6156065b7e96ee369471d778f88a46f9fa39b91a0d89b52afd0067389fca782","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6156065b7e96ee369471d778f88a46f9fa39b91a0d89b52afd0067389fca782","first_computed_at":"2026-05-18T00:50:08.246439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:08.246439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjV4tEUN/XQ08ihpRsJlLvcGbdS+U9+8SloZze6Cdw89UFwSzhK2fNiiuTSzsXbdvSpuokp5RvxbE7xpvYgZBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:08.247014Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.07117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a28f669064a45f6a0edc56f3fb60049a3d023ef07cb65b901e7ecbf4676333f4","sha256:d3cc3cdbadb660825d2e7050be5ee5e501dd97f8a390fe406d59398f6e7ae323"],"state_sha256":"2843fdb53df3a565a23e8066a1365bcf0bda38ecf5dfbffa053c3bb8203325cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l9FjF0MwRdFKZ66ZOgTyokdKSWno0nlWkyuJmcLGpPRxWXUjZcwRUIUqt3KPHSSMQea6lSC4nQRwOk6gyAX8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T13:10:42.976186Z","bundle_sha256":"3a8f021feedda14150f39d7427cca169ff977c2566465908056a52d395d2d7a9"}}