{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Z5CNCVF3C5C4KD2FL2EDWNK2M6","short_pith_number":"pith:Z5CNCVF3","canonical_record":{"source":{"id":"2109.09894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"4050a1a3e88243627b07287ddff44cada111ebab29f88a9ada0d194520ca53a3","abstract_canon_sha256":"c688c1701ffa37176ecf440414133cb74dadda1c1e0e1686b42d6a585664b952"},"schema_version":"1.0"},"canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","source":{"kind":"arxiv","id":"2109.09894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09894","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09894v1","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09894","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"Z5CNCVF3C5C4","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"Z5CNCVF3C5C4KD2F","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"Z5CNCVF3","created_at":"2026-07-05T03:15:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Z5CNCVF3C5C4KD2FL2EDWNK2M6","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"4050a1a3e88243627b07287ddff44cada111ebab29f88a9ada0d194520ca53a3","abstract_canon_sha256":"c688c1701ffa37176ecf440414133cb74dadda1c1e0e1686b42d6a585664b952"},"schema_version":"1.0"},"canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:55.559851Z","signature_b64":"15bpdkosNQsH5212ob3e1tUGCxuv21K+SBdkqqVYgxJCDFdrbyEoxH/B5kOGbznf8UuGlB15mke2/v12RhnSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","last_reissued_at":"2026-07-05T03:15:55.559389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:55.559389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09894","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":"2026-07-05T03:15:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsNH+sfQuUALmUFU9xYEggTb6wUkV/t+zqvFg5yK+07q5T2X2B1/W7vLKEP/tVSxfr2h0KA72UC6ivOQYvoUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:37:24.406803Z"},"content_sha256":"c76261cdc647a24aa4a3dda1c34d4cb504d774299311366600b565a612e7af10","schema_version":"1.0","event_id":"sha256:c76261cdc647a24aa4a3dda1c34d4cb504d774299311366600b565a612e7af10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Z5CNCVF3C5C4KD2FL2EDWNK2M6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Learning for Short Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyan Huang, Hui Yin, Jianxin Li, Shuiqiao Yang, Xiangyu Song","submitted_at":"2021-09-21T00:30:24Z","abstract_excerpt":"Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09894","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/2109.09894/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":"2026-07-05T03:15:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYrAsTLfg51JGS/scwhIiSfs1VlJASdqcGg18CJLoR/j77aCX8VCm5P4nmQIeB1b2QiDYlzd7PuLKPHfdls7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:37:24.407171Z"},"content_sha256":"f95daa7a405c2e5f4ec904fb5489b9f191a5f5219101e5e4ee25dbba825740fc","schema_version":"1.0","event_id":"sha256:f95daa7a405c2e5f4ec904fb5489b9f191a5f5219101e5e4ee25dbba825740fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/bundle.json","state_url":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/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":"2026-07-06T19:37:24Z","links":{"resolver":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6","bundle":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/bundle.json","state":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Z5CNCVF3C5C4KD2FL2EDWNK2M6","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":"c688c1701ffa37176ecf440414133cb74dadda1c1e0e1686b42d6a585664b952","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","title_canon_sha256":"4050a1a3e88243627b07287ddff44cada111ebab29f88a9ada0d194520ca53a3"},"schema_version":"1.0","source":{"id":"2109.09894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09894","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09894v1","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09894","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"Z5CNCVF3C5C4","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"Z5CNCVF3C5C4KD2F","created_at":"2026-07-05T03:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"Z5CNCVF3","created_at":"2026-07-05T03:15:55Z"}],"graph_snapshots":[{"event_id":"sha256:f95daa7a405c2e5f4ec904fb5489b9f191a5f5219101e5e4ee25dbba825740fc","target":"graph","created_at":"2026-07-05T03:15:55Z","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/2109.09894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework ","authors_text":"Guangyan Huang, Hui Yin, Jianxin Li, Shuiqiao Yang, Xiangyu Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","title":"Representation Learning for Short Text Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09894","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:c76261cdc647a24aa4a3dda1c34d4cb504d774299311366600b565a612e7af10","target":"record","created_at":"2026-07-05T03:15:55Z","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":"c688c1701ffa37176ecf440414133cb74dadda1c1e0e1686b42d6a585664b952","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","title_canon_sha256":"4050a1a3e88243627b07287ddff44cada111ebab29f88a9ada0d194520ca53a3"},"schema_version":"1.0","source":{"id":"2109.09894","kind":"arxiv","version":1}},"canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","first_computed_at":"2026-07-05T03:15:55.559389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:55.559389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15bpdkosNQsH5212ob3e1tUGCxuv21K+SBdkqqVYgxJCDFdrbyEoxH/B5kOGbznf8UuGlB15mke2/v12RhnSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:55.559851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c76261cdc647a24aa4a3dda1c34d4cb504d774299311366600b565a612e7af10","sha256:f95daa7a405c2e5f4ec904fb5489b9f191a5f5219101e5e4ee25dbba825740fc"],"state_sha256":"2ac244db34b54af5d88a4e0a88c506246d7a796313a0ac4189117389b0f4853d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COYyxsz08H5Kk2jDyTc+UxLuo8k9lvlWBY+COiPf38VdCDW311u4nvB5Uw8EuaS9VGTcKzINtK+TCzyqH/FICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:37:24.409446Z","bundle_sha256":"2be5337158de83eea270ff7ba550250d3f5381783054f829b99ff30af80b3904"}}