{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XJ74FCZEFEDFLTC3KHXNHWBZBF","short_pith_number":"pith:XJ74FCZE","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"},"canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","source":{"kind":"arxiv","id":"2505.06696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06696","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06696v1","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06696","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"XJ74FCZEFEDF","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"XJ74FCZEFEDFLTC3","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"XJ74FCZE","created_at":"2026-07-05T11:01:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XJ74FCZEFEDFLTC3KHXNHWBZBF","target":"record","payload":{"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"},"canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","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"},"source_kind":"arxiv","source_id":"2505.06696","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":"2026-07-05T11:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPGhOsxdGcpH270c3phL7J59fBhvx9WY5wrMQ9oeR1Oc2fPWu0/7flXrSu6dzRBpOFGESkKTuE7ik2g72Ym+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:34:08.036576Z"},"content_sha256":"158a94b7bffb31044a26b153df38f9f03465bcaf95e2dc9c96a0c11b0e235c32","schema_version":"1.0","event_id":"sha256:158a94b7bffb31044a26b153df38f9f03465bcaf95e2dc9c96a0c11b0e235c32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XJ74FCZEFEDFLTC3KHXNHWBZBF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rB1bnj6AsaZ00uVb0hsXf2I0MVpIX6AtAeHUdFllF3ryPScFx02EoVaEgWnDEqvskW7MyOBr5S7a2aMEk7e7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:34:08.037088Z"},"content_sha256":"b65b78f1529010dff2f4ce226926af7774610db23aa44a7d1c0a5281d0a4c1d3","schema_version":"1.0","event_id":"sha256:b65b78f1529010dff2f4ce226926af7774610db23aa44a7d1c0a5281d0a4c1d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/bundle.json","state_url":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/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":"2026-08-21T19:34:08Z","links":{"resolver":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF","bundle":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/bundle.json","state":"https://pith.science/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ74FCZEFEDFLTC3KHXNHWBZBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XJ74FCZEFEDFLTC3KHXNHWBZBF","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":"e2006be6f3ccfbd1a86f8339fb3a09046f3393f64c91de21af8961a32806855f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T16:47:08Z","title_canon_sha256":"5b0caff48208d4e40546ff25c25cdae56e8b7daac04bdb362f10f03effb37485"},"schema_version":"1.0","source":{"id":"2505.06696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06696","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06696v1","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06696","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"XJ74FCZEFEDF","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"XJ74FCZEFEDFLTC3","created_at":"2026-07-05T11:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"XJ74FCZE","created_at":"2026-07-05T11:01:14Z"}],"graph_snapshots":[{"event_id":"sha256:b65b78f1529010dff2f4ce226926af7774610db23aa44a7d1c0a5281d0a4c1d3","target":"graph","created_at":"2026-07-05T11:01:14Z","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/2505.06696/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dominik Koterwa, Maciej \\'Swita{\\l}a","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T16:47:08Z","title":"Enhancing BERTopic with Intermediate Layer Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06696","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":"sha256:158a94b7bffb31044a26b153df38f9f03465bcaf95e2dc9c96a0c11b0e235c32","target":"record","created_at":"2026-07-05T11:01:14Z","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":"e2006be6f3ccfbd1a86f8339fb3a09046f3393f64c91de21af8961a32806855f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T16:47:08Z","title_canon_sha256":"5b0caff48208d4e40546ff25c25cdae56e8b7daac04bdb362f10f03effb37485"},"schema_version":"1.0","source":{"id":"2505.06696","kind":"arxiv","version":1}},"canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba7fc28b24290655cc5b51eed3d83909718934d4dd8aead74afd598dbb1d58e9","first_computed_at":"2026-07-05T11:01:14.447584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:14.447584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J001hvQyay5eHx1UCGv/6ecBLKx2XBXmNSYlKVuEjlTW8TaobdFjA73JIXRrzZhLaptgeVtoeWZrNY2qdE2IDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:14.448025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:158a94b7bffb31044a26b153df38f9f03465bcaf95e2dc9c96a0c11b0e235c32","sha256:b65b78f1529010dff2f4ce226926af7774610db23aa44a7d1c0a5281d0a4c1d3"],"state_sha256":"2904d1e0e9bcaf8e43efb45798be86b0f84dc6ac1cfdb1d2b0591352ab4feaed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zT3TzJrWKWOhpVCYK+hj9UW5oFsDh1jeA6VyK22QyYdgp9kR5tTeR1n2FAO/Y3mE49uRSN/J4AWNCHpxm2GsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:34:08.041585Z","bundle_sha256":"efa7dddf60b33ac85ec8573fb0abdc662c07da51fa236cf3d037eb669f638993"}}