{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7LMEZR5XM6YJ422PANEAN32TF2","short_pith_number":"pith:7LMEZR5X","canonical_record":{"source":{"id":"2505.07157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:31:36Z","cross_cats_sorted":[],"title_canon_sha256":"edab5512237d0171bbfbf8547a5707945ba08bd0fb19640c2c625adda07fb447","abstract_canon_sha256":"3f30ab35223be0b2f4b5b73b19a8b2dd541011fb0087275b91a42323aa13b4ac"},"schema_version":"1.0"},"canonical_sha256":"fad84cc7b767b09e6b4f034806ef532eb988cf6612876b1df9ecac111cb06da8","source":{"kind":"arxiv","id":"2505.07157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07157","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07157v1","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07157","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_12","alias_value":"7LMEZR5XM6YJ","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_16","alias_value":"7LMEZR5XM6YJ422P","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_8","alias_value":"7LMEZR5X","created_at":"2026-07-05T11:01:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7LMEZR5XM6YJ422PANEAN32TF2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:31:36Z","cross_cats_sorted":[],"title_canon_sha256":"edab5512237d0171bbfbf8547a5707945ba08bd0fb19640c2c625adda07fb447","abstract_canon_sha256":"3f30ab35223be0b2f4b5b73b19a8b2dd541011fb0087275b91a42323aa13b4ac"},"schema_version":"1.0"},"canonical_sha256":"fad84cc7b767b09e6b4f034806ef532eb988cf6612876b1df9ecac111cb06da8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:43.408591Z","signature_b64":"nCD8atNq4pxUZlUiw48OZ3AsKQ0ObTdx3oy873Nw0GizIXjolBroz+cNgxaDprioMui8T+LHd43UvSdr6s0ZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad84cc7b767b09e6b4f034806ef532eb988cf6612876b1df9ecac111cb06da8","last_reissued_at":"2026-07-05T11:01:43.408108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:43.408108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07157","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":"2026-07-05T11:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5XzBBlftOpzsA0dAzKUGVy4Xm18Sr920Onyshu62fgvbVuYEXZCC24ANClvS38EXfVKcWUP30EbcZDe34eySDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:12:20.194002Z"},"content_sha256":"3cf70a180804c579beed7c5d3f3d56d72fdc2a4b64f77c2d9ad6afc55e7d91fb","schema_version":"1.0","event_id":"sha256:3cf70a180804c579beed7c5d3f3d56d72fdc2a4b64f77c2d9ad6afc55e7d91fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7LMEZR5XM6YJ422PANEAN32TF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hajar Sakai, Sarah S. Lam","submitted_at":"2025-05-12T00:31:36Z","abstract_excerpt":"Traditional topic models often struggle with contextual nuances and fail to adequately handle polysemy and rare words. This limitation typically results in topics that lack coherence and quality. Large Language Models (LLMs) can mitigate this issue by generating an initial set of topics. However, these raw topics frequently lack refinement and representativeness, which leads to redundancy without lexical similarity and reduced interpretability. This paper introduces HAMLET, a graph-driven architecture for cross-lingual healthcare topic modeling that uses LLMs. The proposed approach leverages n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07157","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/2505.07157/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":"2026-07-05T11:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tx/5PhhrQvfm6P6/xNQf0qXpIAcIn7mLscUXUBPRyHAFMb9ZSC+4Cl2G2k8c8bT5+sNVbuv5H5s9ajBMZ8zvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:12:20.194591Z"},"content_sha256":"c66e21d269d432a854c3575b37b18566f02cc6f0eb6b3a7f9789f672e6f516ff","schema_version":"1.0","event_id":"sha256:c66e21d269d432a854c3575b37b18566f02cc6f0eb6b3a7f9789f672e6f516ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LMEZR5XM6YJ422PANEAN32TF2/bundle.json","state_url":"https://pith.science/pith/7LMEZR5XM6YJ422PANEAN32TF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LMEZR5XM6YJ422PANEAN32TF2/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":"2026-08-19T22:12:20Z","links":{"resolver":"https://pith.science/pith/7LMEZR5XM6YJ422PANEAN32TF2","bundle":"https://pith.science/pith/7LMEZR5XM6YJ422PANEAN32TF2/bundle.json","state":"https://pith.science/pith/7LMEZR5XM6YJ422PANEAN32TF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LMEZR5XM6YJ422PANEAN32TF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7LMEZR5XM6YJ422PANEAN32TF2","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":"3f30ab35223be0b2f4b5b73b19a8b2dd541011fb0087275b91a42323aa13b4ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:31:36Z","title_canon_sha256":"edab5512237d0171bbfbf8547a5707945ba08bd0fb19640c2c625adda07fb447"},"schema_version":"1.0","source":{"id":"2505.07157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07157","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07157v1","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07157","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_12","alias_value":"7LMEZR5XM6YJ","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_16","alias_value":"7LMEZR5XM6YJ422P","created_at":"2026-07-05T11:01:43Z"},{"alias_kind":"pith_short_8","alias_value":"7LMEZR5X","created_at":"2026-07-05T11:01:43Z"}],"graph_snapshots":[{"event_id":"sha256:c66e21d269d432a854c3575b37b18566f02cc6f0eb6b3a7f9789f672e6f516ff","target":"graph","created_at":"2026-07-05T11:01:43Z","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/2505.07157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional topic models often struggle with contextual nuances and fail to adequately handle polysemy and rare words. This limitation typically results in topics that lack coherence and quality. Large Language Models (LLMs) can mitigate this issue by generating an initial set of topics. However, these raw topics frequently lack refinement and representativeness, which leads to redundancy without lexical similarity and reduced interpretability. This paper introduces HAMLET, a graph-driven architecture for cross-lingual healthcare topic modeling that uses LLMs. The proposed approach leverages n","authors_text":"Hajar Sakai, Sarah S. Lam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:31:36Z","title":"HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07157","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":"sha256:3cf70a180804c579beed7c5d3f3d56d72fdc2a4b64f77c2d9ad6afc55e7d91fb","target":"record","created_at":"2026-07-05T11:01:43Z","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":"3f30ab35223be0b2f4b5b73b19a8b2dd541011fb0087275b91a42323aa13b4ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:31:36Z","title_canon_sha256":"edab5512237d0171bbfbf8547a5707945ba08bd0fb19640c2c625adda07fb447"},"schema_version":"1.0","source":{"id":"2505.07157","kind":"arxiv","version":1}},"canonical_sha256":"fad84cc7b767b09e6b4f034806ef532eb988cf6612876b1df9ecac111cb06da8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fad84cc7b767b09e6b4f034806ef532eb988cf6612876b1df9ecac111cb06da8","first_computed_at":"2026-07-05T11:01:43.408108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:43.408108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCD8atNq4pxUZlUiw48OZ3AsKQ0ObTdx3oy873Nw0GizIXjolBroz+cNgxaDprioMui8T+LHd43UvSdr6s0ZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:43.408591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cf70a180804c579beed7c5d3f3d56d72fdc2a4b64f77c2d9ad6afc55e7d91fb","sha256:c66e21d269d432a854c3575b37b18566f02cc6f0eb6b3a7f9789f672e6f516ff"],"state_sha256":"fbd2f56f75b0a0de4ad76f2e851a42cec7c40394dcf6bc0e14e6646c0fa71bbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIXy/VMF+GqMvu20/HzbXXEti/7Qia+OIcZFRx8xc+RL9F7j96m4h+TGrKp6MGU5Gk31v2LTKHcJCR4LwfipCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:12:20.199901Z","bundle_sha256":"6997b722fc244655b2eefc6ecb2efa77f51dae57f4ac518cfef9876d8d98e2a2"}}