{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XJ74FCZEFEDFLTC3KHXNHWBZBF","short_pith_number":"pith:XJ74FCZE","schema_version":"1.0","canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","source":{"kind":"arxiv","id":"2505.06696","version":1},"attestation_state":"computed","paper":{"title":"Enhancing BERTopic with Intermediate Layer Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Koterwa, Maciej \\'Swita{\\l}a","submitted_at":"2025-05-10T16:47:08Z","abstract_excerpt":"BERTopic is a topic modeling algorithm that leverages transformer-based embeddings to create dense clusters, enabling the estimation of topic structures and the extraction of valuable insights from a corpus of documents. This approach allows users to efficiently process large-scale text data and gain meaningful insights into its structure. While BERTopic is a powerful tool, embedding preparation can vary, including extracting representations from intermediate model layers and applying transformations to these embeddings. In this study, we evaluate 18 different embedding representations and pre"},"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":"2505.06696","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T16:47:08Z","cross_cats_sorted":[],"title_canon_sha256":"5b0caff48208d4e40546ff25c25cdae56e8b7daac04bdb362f10f03effb37485","abstract_canon_sha256":"e2006be6f3ccfbd1a86f8339fb3a09046f3393f64c91de21af8961a32806855f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:14.448025Z","signature_b64":"J001hvQyay5eHx1UCGv/6ecBLKx2XBXmNSYlKVuEjlTW8TaobdFjA73JIXRrzZhLaptgeVtoeWZrNY2qdE2IDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","last_reissued_at":"2026-07-05T11:01:14.447584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:14.447584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing BERTopic with Intermediate Layer Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominik Koterwa, Maciej \\'Swita{\\l}a","submitted_at":"2025-05-10T16:47:08Z","abstract_excerpt":"BERTopic is a topic modeling algorithm that leverages transformer-based embeddings to create dense clusters, enabling the estimation of topic structures and the extraction of valuable insights from a corpus of documents. This approach allows users to efficiently process large-scale text data and gain meaningful insights into its structure. While BERTopic is a powerful tool, embedding preparation can vary, including extracting representations from intermediate model layers and applying transformations to these embeddings. In this study, we evaluate 18 different embedding representations and pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06696","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/2505.06696/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":"2505.06696","created_at":"2026-07-05T11:01:14.447637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06696v1","created_at":"2026-07-05T11:01:14.447637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06696","created_at":"2026-07-05T11:01:14.447637+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ74FCZEFEDF","created_at":"2026-07-05T11:01:14.447637+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ74FCZEFEDFLTC3","created_at":"2026-07-05T11:01:14.447637+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ74FCZE","created_at":"2026-07-05T11:01:14.447637+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/XJ74FCZEFEDFLTC3KHXNHWBZBF","json":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF.json","graph_json":"https://pith.science/api/pith-number/XJ74FCZEFEDFLTC3KHXNHWBZBF/graph.json","events_json":"https://pith.science/api/pith-number/XJ74FCZEFEDFLTC3KHXNHWBZBF/events.json","paper":"https://pith.science/paper/XJ74FCZE"},"agent_actions":{"view_html":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF","download_json":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF.json","view_paper":"https://pith.science/paper/XJ74FCZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06696&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ74FCZEFEDFLTC3KHXNHWBZBF/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ74FCZEFEDFLTC3KHXNHWBZBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/action/storage_attestation","attest_author":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/action/author_attestation","sign_citation":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/action/citation_signature","submit_replication":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/action/replication_record"}},"created_at":"2026-07-05T11:01:14.447637+00:00","updated_at":"2026-07-05T11:01:14.447637+00:00"}