{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5V7GHHHMC6ID2WN2UBLWHSCTZJ","short_pith_number":"pith:5V7GHHHM","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"},"canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","source":{"kind":"arxiv","id":"2605.28832","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28832","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28832v1","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28832","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"5V7GHHHMC6ID","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"5V7GHHHMC6ID2WN2","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"5V7GHHHM","created_at":"2026-05-29T00:04:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5V7GHHHMC6ID2WN2UBLWHSCTZJ","target":"record","payload":{"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"},"canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","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"},"source_kind":"arxiv","source_id":"2605.28832","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":"2026-05-29T00:04:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7p52OPzQGuzmr0SC45WQ1JIyj1LRojVvcPK6s9q3E9PljzYp4X2tUc+elY4xFN15Dvgupu5ZBLNL8pIoUgNwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:35:02.451216Z"},"content_sha256":"19d22623e19173b59ea20b2c96f734f24839f312b3211ab067e7804bc4ad3baa","schema_version":"1.0","event_id":"sha256:19d22623e19173b59ea20b2c96f734f24839f312b3211ab067e7804bc4ad3baa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5V7GHHHMC6ID2WN2UBLWHSCTZJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T00:04:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUBjWh6nAF3CnBDSyZh/Gk2mO98kX9HkUJ0mXgreT2+0lAeplahiLA184Q/beR2aYDwaDYbOcbsPgZ5A/JJnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:35:02.451622Z"},"content_sha256":"1d3d30f8605c911a36e17ed7c8c4d92a1920c67d66ba256cd94bc9263850c92f","schema_version":"1.0","event_id":"sha256:1d3d30f8605c911a36e17ed7c8c4d92a1920c67d66ba256cd94bc9263850c92f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/bundle.json","state_url":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/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":"2026-05-30T23:35:02Z","links":{"resolver":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ","bundle":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/bundle.json","state":"https://pith.science/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5V7GHHHMC6ID2WN2UBLWHSCTZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5V7GHHHMC6ID2WN2UBLWHSCTZJ","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":"a17de0e6edcd174f61f17aef40d60122d2d90fe9e2d3931eecc2cef8ca95f717","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T08:34:47Z","title_canon_sha256":"a633cce018d4a6feb9f85be6067f90560c3fdda2f5883f8f67bd6965648e869d"},"schema_version":"1.0","source":{"id":"2605.28832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28832","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28832v1","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28832","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"5V7GHHHMC6ID","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"5V7GHHHMC6ID2WN2","created_at":"2026-05-29T00:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"5V7GHHHM","created_at":"2026-05-29T00:04:13Z"}],"graph_snapshots":[{"event_id":"sha256:1d3d30f8605c911a36e17ed7c8c4d92a1920c67d66ba256cd94bc9263850c92f","target":"graph","created_at":"2026-05-29T00:04:13Z","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/2605.28832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alex Ding, Jason Yang, Tarun Rapaka, Willy Rodriguez","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T08:34:47Z","title":"A comparative study of transformer-based embeddings for topic coherence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28832","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":"sha256:19d22623e19173b59ea20b2c96f734f24839f312b3211ab067e7804bc4ad3baa","target":"record","created_at":"2026-05-29T00:04:13Z","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":"a17de0e6edcd174f61f17aef40d60122d2d90fe9e2d3931eecc2cef8ca95f717","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T08:34:47Z","title_canon_sha256":"a633cce018d4a6feb9f85be6067f90560c3fdda2f5883f8f67bd6965648e869d"},"schema_version":"1.0","source":{"id":"2605.28832","kind":"arxiv","version":1}},"canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed7e639cec17903d59baa05763c853ca5294baaf721831278a01a0f92c154452","first_computed_at":"2026-05-29T00:04:13.362160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:13.362160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FMWgzIwPdAq1qshW2jaqhPDwJ/1a1x5d104H8k24tyM87LThi4+3+VWlzGgQjsJTTSizJA66OmoYooH14r9FDw==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:13.363055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19d22623e19173b59ea20b2c96f734f24839f312b3211ab067e7804bc4ad3baa","sha256:1d3d30f8605c911a36e17ed7c8c4d92a1920c67d66ba256cd94bc9263850c92f"],"state_sha256":"aa819cc42de4955785603596e7e5d55141775583e94a2173155b140669ea73ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GrCc/P/5TppmtiMDTl4ZxTdzIt7Pnwg7SpDCbRPJeX0qxsej7JqcyAovIDzY3kZmy3E9nlnT2io84r2Dh0Q+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:35:02.453872Z","bundle_sha256":"f35ac1ca7f10ecab64fb652638ab5ad66e2ecf0fc7d135848ab0bb8fc1c23f0c"}}