{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6BVH7Z75LR5GGWF2V4ZPAHXLXV","short_pith_number":"pith:6BVH7Z75","schema_version":"1.0","canonical_sha256":"f06a7fe7fd5c7a6358baaf32f01eebbd6c385b96c495172a69059eebfef367d7","source":{"kind":"arxiv","id":"2607.10548","version":1},"attestation_state":"computed","paper":{"title":"Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Li, Jixuan Yin, Yuxuan Gu, Zhihao Yao","submitted_at":"2026-07-12T03:22:12Z","abstract_excerpt":"Pseudo-labeling based on Optimal Transport (OT) has become an effective mechanism for enhancing short text clustering. Existing OT methods are short in modeling semantic consistencies between samples, which may assign different pseudo-labels to semantically similar samples. These erroneous pseudo-labels can cause the model to produce inferior clusters. This paper proposes a novel short text clustering framework, which remedies the neglect of semantic consistency in existing OT methods, generating reliable pseudo-labels to facilitate clustering. Specifically, the proposed approach first designs"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.10548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-12T03:22:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d951e83bb966fa0c8283467547446abbc7e675a774a55936356e3084a62695b5","abstract_canon_sha256":"c3a26724c35a713db710591954ecc39c6eff51f27ae0604a6477d7f3d196a3ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:20.755076Z","signature_b64":"MBFwA20jW0sNncKq77FVdZNgWq5HDf0Xe7+CKr0RHGQ4H2MIeb1Aa6u1CanQx16F867aNBngSV4tmfVCkRAJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06a7fe7fd5c7a6358baaf32f01eebbd6c385b96c495172a69059eebfef367d7","last_reissued_at":"2026-07-14T01:21:20.754232Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:20.754232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Li, Jixuan Yin, Yuxuan Gu, Zhihao Yao","submitted_at":"2026-07-12T03:22:12Z","abstract_excerpt":"Pseudo-labeling based on Optimal Transport (OT) has become an effective mechanism for enhancing short text clustering. Existing OT methods are short in modeling semantic consistencies between samples, which may assign different pseudo-labels to semantically similar samples. These erroneous pseudo-labels can cause the model to produce inferior clusters. This paper proposes a novel short text clustering framework, which remedies the neglect of semantic consistency in existing OT methods, generating reliable pseudo-labels to facilitate clustering. Specifically, the proposed approach first designs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10548","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/2607.10548/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.10548","created_at":"2026-07-14T01:21:20.754678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10548v1","created_at":"2026-07-14T01:21:20.754678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10548","created_at":"2026-07-14T01:21:20.754678+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BVH7Z75LR5G","created_at":"2026-07-14T01:21:20.754678+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BVH7Z75LR5GGWF2","created_at":"2026-07-14T01:21:20.754678+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BVH7Z75","created_at":"2026-07-14T01:21:20.754678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV","json":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV.json","graph_json":"https://pith.science/api/pith-number/6BVH7Z75LR5GGWF2V4ZPAHXLXV/graph.json","events_json":"https://pith.science/api/pith-number/6BVH7Z75LR5GGWF2V4ZPAHXLXV/events.json","paper":"https://pith.science/paper/6BVH7Z75"},"agent_actions":{"view_html":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV","download_json":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV.json","view_paper":"https://pith.science/paper/6BVH7Z75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10548&json=true","fetch_graph":"https://pith.science/api/pith-number/6BVH7Z75LR5GGWF2V4ZPAHXLXV/graph.json","fetch_events":"https://pith.science/api/pith-number/6BVH7Z75LR5GGWF2V4ZPAHXLXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV/action/storage_attestation","attest_author":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV/action/author_attestation","sign_citation":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV/action/citation_signature","submit_replication":"https://pith.science/pith/6BVH7Z75LR5GGWF2V4ZPAHXLXV/action/replication_record"}},"created_at":"2026-07-14T01:21:20.754678+00:00","updated_at":"2026-07-14T01:21:20.754678+00:00"}