{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4JIXRPUIHRUGMIVX3GTZMAI7XT","short_pith_number":"pith:4JIXRPUI","canonical_record":{"source":{"id":"2211.12878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"e9e81b160cc566dd624e376bcf9f9733ae560819664a16333e9d2d31a81d7c8c","abstract_canon_sha256":"b492f26e79076ca02a2a19a29297434c985923e0d185e5fcfde4f1654eb3e639"},"schema_version":"1.0"},"canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","source":{"kind":"arxiv","id":"2211.12878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12878","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12878v1","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12878","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"4JIXRPUIHRUG","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"4JIXRPUIHRUGMIVX","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"4JIXRPUI","created_at":"2026-07-05T05:18:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4JIXRPUIHRUGMIVX3GTZMAI7XT","target":"record","payload":{"canonical_record":{"source":{"id":"2211.12878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"e9e81b160cc566dd624e376bcf9f9733ae560819664a16333e9d2d31a81d7c8c","abstract_canon_sha256":"b492f26e79076ca02a2a19a29297434c985923e0d185e5fcfde4f1654eb3e639"},"schema_version":"1.0"},"canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:55.943718Z","signature_b64":"XfzmKumBcMZUHfKH1BBYUEMJbnwX0r0kvJouZt3Q2/zZV5zHQz0j8WOsJXbyIhEJiKbv2IwzWeGDBMHZfXbYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","last_reissued_at":"2026-07-05T05:18:55.943330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:55.943330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.12878","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":"2026-07-05T05:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVVRlbuDICrVqyDSzYoeBo6tkLmFVznbV9mOLq9lataiPuIvOmzdJ4VFFRUvaVZMc3E/pYIFZc9rtmrzUQQoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:03:40.873981Z"},"content_sha256":"143bcd915783213d5e8629af444e52a975c1f1580448a42707471dd2a6c3e538","schema_version":"1.0","event_id":"sha256:143bcd915783213d5e8629af444e52a975c1f1580448a42707471dd2a6c3e538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4JIXRPUIHRUGMIVX3GTZMAI7XT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Xiaobao Wu, Xinshuai Dong","submitted_at":"2022-11-23T11:33:43Z","abstract_excerpt":"To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information. However, most of them do not make full use of the augmented data or the data characteristic: they insufficiently learn the relations among samples in data, leading to dissimilar topic distributions of semantically similar text pairs. To better address data sparsity, in this paper we propose a novel short text topic modeling framework, Topic-Semantic Contrastive Topic Model (TSCTM). To su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12878","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.12878/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":"2026-07-05T05:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gK702r6+CW45ym/+SqoRRmjruyB/VShvCAHyYOWRAkFyqyT4Ig8Sx8uxgLgYHaT6fcpRXl9x2BoztQivQ8arAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:03:40.874823Z"},"content_sha256":"7882e7e9a4b6ad1482ece294a8630ac337336aaf84514f5a38ed5bb5e62536db","schema_version":"1.0","event_id":"sha256:7882e7e9a4b6ad1482ece294a8630ac337336aaf84514f5a38ed5bb5e62536db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/bundle.json","state_url":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/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":"2026-08-16T12:03:40Z","links":{"resolver":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT","bundle":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/bundle.json","state":"https://pith.science/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JIXRPUIHRUGMIVX3GTZMAI7XT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4JIXRPUIHRUGMIVX3GTZMAI7XT","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":"b492f26e79076ca02a2a19a29297434c985923e0d185e5fcfde4f1654eb3e639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","title_canon_sha256":"e9e81b160cc566dd624e376bcf9f9733ae560819664a16333e9d2d31a81d7c8c"},"schema_version":"1.0","source":{"id":"2211.12878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12878","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12878v1","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12878","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"4JIXRPUIHRUG","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"4JIXRPUIHRUGMIVX","created_at":"2026-07-05T05:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"4JIXRPUI","created_at":"2026-07-05T05:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:7882e7e9a4b6ad1482ece294a8630ac337336aaf84514f5a38ed5bb5e62536db","target":"graph","created_at":"2026-07-05T05:18:55Z","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/2211.12878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information. However, most of them do not make full use of the augmented data or the data characteristic: they insufficiently learn the relations among samples in data, leading to dissimilar topic distributions of semantically similar text pairs. To better address data sparsity, in this paper we propose a novel short text topic modeling framework, Topic-Semantic Contrastive Topic Model (TSCTM). To su","authors_text":"Anh Tuan Luu, Xiaobao Wu, Xinshuai Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","title":"Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12878","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":"sha256:143bcd915783213d5e8629af444e52a975c1f1580448a42707471dd2a6c3e538","target":"record","created_at":"2026-07-05T05:18:55Z","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":"b492f26e79076ca02a2a19a29297434c985923e0d185e5fcfde4f1654eb3e639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T11:33:43Z","title_canon_sha256":"e9e81b160cc566dd624e376bcf9f9733ae560819664a16333e9d2d31a81d7c8c"},"schema_version":"1.0","source":{"id":"2211.12878","kind":"arxiv","version":1}},"canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e25178be883c686622b7d9a796011fbcdee730fa12e045dab13b204a640cbf42","first_computed_at":"2026-07-05T05:18:55.943330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:55.943330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XfzmKumBcMZUHfKH1BBYUEMJbnwX0r0kvJouZt3Q2/zZV5zHQz0j8WOsJXbyIhEJiKbv2IwzWeGDBMHZfXbYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:55.943718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:143bcd915783213d5e8629af444e52a975c1f1580448a42707471dd2a6c3e538","sha256:7882e7e9a4b6ad1482ece294a8630ac337336aaf84514f5a38ed5bb5e62536db"],"state_sha256":"e98899fc728722b91d5f283a0ca0020dde195cb0995dacdc3e9586be60a78156"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZakjuKe2L2WUtEiPv/iYduc+83Kv1RVmmkNFDFL+eS7y19axgZq2Aq5xGj+uKCoW73kvp9wGTvaQNVSaEzTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:03:40.880411Z","bundle_sha256":"61e8b7def7363bf2bbd5273cded9761c3361273ac0a02953b42f1264965d3483"}}