{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IMCCJSUPFDH7TVRJ4VN2U6TX25","short_pith_number":"pith:IMCCJSUP","canonical_record":{"source":{"id":"2601.12154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T20:06:14Z","cross_cats_sorted":[],"title_canon_sha256":"2472e3a16120997fd65fc693c8c334a4077af59fa0498719aac51c8550bd3119","abstract_canon_sha256":"d4e77f09bc455f58ff921ad78d0e39e8c66d251abf7f1a8ee0d158e95b433eff"},"schema_version":"1.0"},"canonical_sha256":"430424ca8f28cff9d629e55baa7a77d770cf016332ef7b37f98fc92ef4f26d19","source":{"kind":"arxiv","id":"2601.12154","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12154","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12154v2","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12154","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMCCJSUPFDH7","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"IMCCJSUPFDH7TVRJ","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"IMCCJSUP","created_at":"2026-05-28T01:05:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IMCCJSUPFDH7TVRJ4VN2U6TX25","target":"record","payload":{"canonical_record":{"source":{"id":"2601.12154","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T20:06:14Z","cross_cats_sorted":[],"title_canon_sha256":"2472e3a16120997fd65fc693c8c334a4077af59fa0498719aac51c8550bd3119","abstract_canon_sha256":"d4e77f09bc455f58ff921ad78d0e39e8c66d251abf7f1a8ee0d158e95b433eff"},"schema_version":"1.0"},"canonical_sha256":"430424ca8f28cff9d629e55baa7a77d770cf016332ef7b37f98fc92ef4f26d19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:11.485668Z","signature_b64":"L6G4VXswW4d3srKhuE15sraJsTF/GfNcvdu3kWQd3HG9Qtq6NY96RwM00tJVdDjR4dlAsX5feavFPDHgGLSTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"430424ca8f28cff9d629e55baa7a77d770cf016332ef7b37f98fc92ef4f26d19","last_reissued_at":"2026-05-28T01:05:11.485132Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:11.485132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.12154","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0ME8dwkp5iPCriljzD8HbmAApL9e7YxT5nLE4nPRSQtQyEZ00/rMhTc9++n7213I2rg/qLFa7PNnSG9kcyCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:29:51.844474Z"},"content_sha256":"85e71ac85058bf92d8e275ec461a5e46ebb7b2e2e4f5d83f8c4b5b8d6b643cf3","schema_version":"1.0","event_id":"sha256:85e71ac85058bf92d8e275ec461a5e46ebb7b2e2e4f5d83f8c4b5b8d6b643cf3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IMCCJSUPFDH7TVRJ4VN2U6TX25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing Cancer Patients' Experiences with Embedding-based Topic Modeling and LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Stiggelbout, Jan Heijdra Suasnabar, Lifeng Han, Suzan Verberne, Teodor-C\\u{a}lin Ionescu","submitted_at":"2026-01-17T20:06:14Z","abstract_excerpt":"This study investigates the use of neural topic modeling and LLMs to uncover meaningful themes from patient storytelling data, to offer insights that could contribute to more patient-oriented healthcare practices. We analyze a collection of transcribed interviews with cancer patients (132,722 words in 13 interviews). We first evaluate BERTopic and Top2Vec for individual interview summarization by using similar preprocessing, chunking, and clustering configurations to ensure a fair comparison on Keyword Extraction. LLMs (GPT4) are then used for the next step topic labeling. Their outputs for a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12154","kind":"arxiv","version":2},"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/2601.12154/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":"2026-05-28T01:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t2T7CNq6FGQhOKO+PN8ETgc9tEz7osyW3TAdr9JgO3IKCJL4C3BKX3rNoBxGEsJgO+MyGDF04awY+HoD7boiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:29:51.844853Z"},"content_sha256":"913a5ec61d2f490b40d57b128a7ea85e0e46bfdc010ffb83644daaed2e125eef","schema_version":"1.0","event_id":"sha256:913a5ec61d2f490b40d57b128a7ea85e0e46bfdc010ffb83644daaed2e125eef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/bundle.json","state_url":"https://pith.science/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/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":"2026-07-04T18:29:51Z","links":{"resolver":"https://pith.science/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25","bundle":"https://pith.science/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/bundle.json","state":"https://pith.science/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMCCJSUPFDH7TVRJ4VN2U6TX25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMCCJSUPFDH7TVRJ4VN2U6TX25","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":"d4e77f09bc455f58ff921ad78d0e39e8c66d251abf7f1a8ee0d158e95b433eff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T20:06:14Z","title_canon_sha256":"2472e3a16120997fd65fc693c8c334a4077af59fa0498719aac51c8550bd3119"},"schema_version":"1.0","source":{"id":"2601.12154","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12154","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12154v2","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12154","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMCCJSUPFDH7","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"IMCCJSUPFDH7TVRJ","created_at":"2026-05-28T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"IMCCJSUP","created_at":"2026-05-28T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:913a5ec61d2f490b40d57b128a7ea85e0e46bfdc010ffb83644daaed2e125eef","target":"graph","created_at":"2026-05-28T01:05:11Z","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/2601.12154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates the use of neural topic modeling and LLMs to uncover meaningful themes from patient storytelling data, to offer insights that could contribute to more patient-oriented healthcare practices. We analyze a collection of transcribed interviews with cancer patients (132,722 words in 13 interviews). We first evaluate BERTopic and Top2Vec for individual interview summarization by using similar preprocessing, chunking, and clustering configurations to ensure a fair comparison on Keyword Extraction. LLMs (GPT4) are then used for the next step topic labeling. Their outputs for a ","authors_text":"Anne Stiggelbout, Jan Heijdra Suasnabar, Lifeng Han, Suzan Verberne, Teodor-C\\u{a}lin Ionescu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T20:06:14Z","title":"Analyzing Cancer Patients' Experiences with Embedding-based Topic Modeling and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12154","kind":"arxiv","version":2},"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":"sha256:85e71ac85058bf92d8e275ec461a5e46ebb7b2e2e4f5d83f8c4b5b8d6b643cf3","target":"record","created_at":"2026-05-28T01:05:11Z","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":"d4e77f09bc455f58ff921ad78d0e39e8c66d251abf7f1a8ee0d158e95b433eff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T20:06:14Z","title_canon_sha256":"2472e3a16120997fd65fc693c8c334a4077af59fa0498719aac51c8550bd3119"},"schema_version":"1.0","source":{"id":"2601.12154","kind":"arxiv","version":2}},"canonical_sha256":"430424ca8f28cff9d629e55baa7a77d770cf016332ef7b37f98fc92ef4f26d19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"430424ca8f28cff9d629e55baa7a77d770cf016332ef7b37f98fc92ef4f26d19","first_computed_at":"2026-05-28T01:05:11.485132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:11.485132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L6G4VXswW4d3srKhuE15sraJsTF/GfNcvdu3kWQd3HG9Qtq6NY96RwM00tJVdDjR4dlAsX5feavFPDHgGLSTCg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:11.485668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.12154","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e71ac85058bf92d8e275ec461a5e46ebb7b2e2e4f5d83f8c4b5b8d6b643cf3","sha256:913a5ec61d2f490b40d57b128a7ea85e0e46bfdc010ffb83644daaed2e125eef"],"state_sha256":"5498eb585f7d49119cdb00816e5282ca88b051bd187b5a081e96df771912502c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWcc3xi/QJ6VhT2NDMrQHYGrjIU9yooZbvo6XB9aQWfvBZBpUG1QQYH/jWCYuAU8CFpVacrO/cKUm4EhqvtpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:29:51.847017Z","bundle_sha256":"fa55eb72a7c2a5c8a814fe04e4fc42d817ff0aca151688d77f904a1aebf1381c"}}