{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5V7GHHHMC6ID2WN2UBLWHSCTZJ","short_pith_number":"pith:5V7GHHHM","schema_version":"1.0","canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","source":{"kind":"arxiv","id":"2605.28832","version":1},"attestation_state":"computed","paper":{"title":"A comparative study of transformer-based embeddings for topic coherence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Ding, Jason Yang, Tarun Rapaka, Willy Rodriguez","submitted_at":"2026-04-10T08:34:47Z","abstract_excerpt":"Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most widely used and interpretable probabilistic approaches. Recent advances in NLP, particularly transformer-based language models, offer improved document representations. It is also known that the size of the model (in terms of number of parameters) has a significant impact in the performance of the language models on different pre-defined tasks. In this stud"},"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":"2605.28832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T08:34:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a633cce018d4a6feb9f85be6067f90560c3fdda2f5883f8f67bd6965648e869d","abstract_canon_sha256":"a17de0e6edcd174f61f17aef40d60122d2d90fe9e2d3931eecc2cef8ca95f717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:13.363055Z","signature_b64":"FMWgzIwPdAq1qshW2jaqhPDwJ/1a1x5d104H8k24tyM87LThi4+3+VWlzGgQjsJTTSizJA66OmoYooH14r9FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","last_reissued_at":"2026-05-29T00:04:13.362160Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:13.362160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparative study of transformer-based embeddings for topic coherence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Ding, Jason Yang, Tarun Rapaka, Willy Rodriguez","submitted_at":"2026-04-10T08:34:47Z","abstract_excerpt":"Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most widely used and interpretable probabilistic approaches. Recent advances in NLP, particularly transformer-based language models, offer improved document representations. It is also known that the size of the model (in terms of number of parameters) has a significant impact in the performance of the language models on different pre-defined tasks. In this stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28832","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/2605.28832/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":"2605.28832","created_at":"2026-05-29T00:04:13.362277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28832v1","created_at":"2026-05-29T00:04:13.362277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28832","created_at":"2026-05-29T00:04:13.362277+00:00"},{"alias_kind":"pith_short_12","alias_value":"5V7GHHHMC6ID","created_at":"2026-05-29T00:04:13.362277+00:00"},{"alias_kind":"pith_short_16","alias_value":"5V7GHHHMC6ID2WN2","created_at":"2026-05-29T00:04:13.362277+00:00"},{"alias_kind":"pith_short_8","alias_value":"5V7GHHHM","created_at":"2026-05-29T00:04:13.362277+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/5V7GHHHMC6ID2WN2UBLWHSCTZJ","json":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ.json","graph_json":"https://pith.science/api/pith-number/5V7GHHHMC6ID2WN2UBLWHSCTZJ/graph.json","events_json":"https://pith.science/api/pith-number/5V7GHHHMC6ID2WN2UBLWHSCTZJ/events.json","paper":"https://pith.science/paper/5V7GHHHM"},"agent_actions":{"view_html":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ","download_json":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ.json","view_paper":"https://pith.science/paper/5V7GHHHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28832&json=true","fetch_graph":"https://pith.science/api/pith-number/5V7GHHHMC6ID2WN2UBLWHSCTZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5V7GHHHMC6ID2WN2UBLWHSCTZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/action/storage_attestation","attest_author":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/action/author_attestation","sign_citation":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/action/citation_signature","submit_replication":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/action/replication_record"}},"created_at":"2026-05-29T00:04:13.362277+00:00","updated_at":"2026-05-29T00:04:13.362277+00:00"}