{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PWZDETMW43JCSDGXO6ZL5YCRTF","short_pith_number":"pith:PWZDETMW","canonical_record":{"source":{"id":"2305.16335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:43:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5000348588658b03070a5863677ae7be084e41f1b047abd9f1bd3cbcbf415532","abstract_canon_sha256":"ff627bcd335a06a31b17c8fcfcb72c0d0e91961202b47f69b9756cf5a139150f"},"schema_version":"1.0"},"canonical_sha256":"7db2324d96e6d2290cd777b2bee051994128fd913b5c33c111ab31edc50c055f","source":{"kind":"arxiv","id":"2305.16335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16335","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16335v1","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16335","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"PWZDETMW43JC","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"PWZDETMW43JCSDGX","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"PWZDETMW","created_at":"2026-07-05T06:14:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PWZDETMW43JCSDGXO6ZL5YCRTF","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:43:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5000348588658b03070a5863677ae7be084e41f1b047abd9f1bd3cbcbf415532","abstract_canon_sha256":"ff627bcd335a06a31b17c8fcfcb72c0d0e91961202b47f69b9756cf5a139150f"},"schema_version":"1.0"},"canonical_sha256":"7db2324d96e6d2290cd777b2bee051994128fd913b5c33c111ab31edc50c055f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:11.953284Z","signature_b64":"L/VsDUvEKh0BbqQjKCHr5FQH8i/I9VvRxiSBBSNYPIiZf0RpDV5pW4ovN0omAfkBBi9/+6jUo2QOFB8JeliFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db2324d96e6d2290cd777b2bee051994128fd913b5c33c111ab31edc50c055f","last_reissued_at":"2026-07-05T06:14:11.952934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:11.952934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16335","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":"2026-07-05T06:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcEC9Oa4pda8nWJzJIcR+Y9ytxwcj3g36xNnQybfYVJY0mYqJBrxxIe68gk0nRHQP7/P89dOVUTGdXUf7+y9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:55:00.960481Z"},"content_sha256":"e989dc35c24f388d2b0d25188794a0ab35fc3c124cf62b43c004d342bf10ff07","schema_version":"1.0","event_id":"sha256:e989dc35c24f388d2b0d25188794a0ab35fc3c124cf62b43c004d342bf10ff07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PWZDETMW43JCSDGXO6ZL5YCRTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chaochao Chen, Mengling Hu, Weiming Liu, Xiaolin Zheng, Xinting Liao","submitted_at":"2023-05-23T12:43:40Z","abstract_excerpt":"Short text clustering is challenging since it takes imbalanced and noisy data as inputs. Existing approaches cannot solve this problem well, since (1) they are prone to obtain degenerate solutions especially on heavy imbalanced datasets, and (2) they are vulnerable to noises. To tackle the above issues, we propose a Robust Short Text Clustering (RSTC) model to improve robustness against imbalanced and noisy data. RSTC includes two modules, i.e., pseudo-label generation module and robust representation learning module. The former generates pseudo-labels to provide supervision for the later, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16335","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/2305.16335/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":"2026-07-05T06:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWiUvvTi+FI41LLxl3an+dm+jH6Ty+KcnrDo35OtoZ5SghdzP2+AAPcoRfpcid1fMbEJdgx9PfGgqnM5evb1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:55:00.960989Z"},"content_sha256":"df34b57631ee360cff40aef093ffa6d5c3ac63c9a12eda45266b85168b7a9147","schema_version":"1.0","event_id":"sha256:df34b57631ee360cff40aef093ffa6d5c3ac63c9a12eda45266b85168b7a9147"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/bundle.json","state_url":"https://pith.science/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/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":"2026-08-10T09:55:00Z","links":{"resolver":"https://pith.science/pith/PWZDETMW43JCSDGXO6ZL5YCRTF","bundle":"https://pith.science/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/bundle.json","state":"https://pith.science/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWZDETMW43JCSDGXO6ZL5YCRTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PWZDETMW43JCSDGXO6ZL5YCRTF","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":"ff627bcd335a06a31b17c8fcfcb72c0d0e91961202b47f69b9756cf5a139150f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:43:40Z","title_canon_sha256":"5000348588658b03070a5863677ae7be084e41f1b047abd9f1bd3cbcbf415532"},"schema_version":"1.0","source":{"id":"2305.16335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16335","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16335v1","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16335","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"PWZDETMW43JC","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"PWZDETMW43JCSDGX","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"PWZDETMW","created_at":"2026-07-05T06:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:df34b57631ee360cff40aef093ffa6d5c3ac63c9a12eda45266b85168b7a9147","target":"graph","created_at":"2026-07-05T06:14:11Z","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/2305.16335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Short text clustering is challenging since it takes imbalanced and noisy data as inputs. Existing approaches cannot solve this problem well, since (1) they are prone to obtain degenerate solutions especially on heavy imbalanced datasets, and (2) they are vulnerable to noises. To tackle the above issues, we propose a Robust Short Text Clustering (RSTC) model to improve robustness against imbalanced and noisy data. RSTC includes two modules, i.e., pseudo-label generation module and robust representation learning module. The former generates pseudo-labels to provide supervision for the later, whi","authors_text":"Chaochao Chen, Mengling Hu, Weiming Liu, Xiaolin Zheng, Xinting Liao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:43:40Z","title":"Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16335","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:e989dc35c24f388d2b0d25188794a0ab35fc3c124cf62b43c004d342bf10ff07","target":"record","created_at":"2026-07-05T06:14:11Z","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":"ff627bcd335a06a31b17c8fcfcb72c0d0e91961202b47f69b9756cf5a139150f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:43:40Z","title_canon_sha256":"5000348588658b03070a5863677ae7be084e41f1b047abd9f1bd3cbcbf415532"},"schema_version":"1.0","source":{"id":"2305.16335","kind":"arxiv","version":1}},"canonical_sha256":"7db2324d96e6d2290cd777b2bee051994128fd913b5c33c111ab31edc50c055f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7db2324d96e6d2290cd777b2bee051994128fd913b5c33c111ab31edc50c055f","first_computed_at":"2026-07-05T06:14:11.952934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:11.952934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/VsDUvEKh0BbqQjKCHr5FQH8i/I9VvRxiSBBSNYPIiZf0RpDV5pW4ovN0omAfkBBi9/+6jUo2QOFB8JeliFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:11.953284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e989dc35c24f388d2b0d25188794a0ab35fc3c124cf62b43c004d342bf10ff07","sha256:df34b57631ee360cff40aef093ffa6d5c3ac63c9a12eda45266b85168b7a9147"],"state_sha256":"11042adbc21dd1a25f891f2c7b9124879b3ef195f47d74185d3158fdbf82369e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RWzZMwYTm6asvIRTHRf6WCrBp4Om2v1XnaEUs0gPMJmwWUI1ASzCqZDvyHi/U/6y++opuvlytftQCUm46xtRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:55:00.965734Z","bundle_sha256":"230857245a88cb2f8f7b9af3f25cfbc394bcbe86643d78697918af915aefad3f"}}