{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7TBMW4D7UA2FJHQ6BVWUIAO222","short_pith_number":"pith:7TBMW4D7","canonical_record":{"source":{"id":"2605.03299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T02:40:39Z","cross_cats_sorted":[],"title_canon_sha256":"7898ab9d9a558b58cd4fec01e4504898656b4ffbe6b7a9dcbcac43bdb78bc117","abstract_canon_sha256":"48b9122eecbe939d894b2eb48e335253c8899e151e935b32dae8b0de78d92acc"},"schema_version":"1.0"},"canonical_sha256":"fcc2cb707fa034549e1e0d6d4401dad6b8e28ae25d99d55aa23d78f599ecc02c","source":{"kind":"arxiv","id":"2605.03299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03299","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03299v2","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03299","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"7TBMW4D7UA2F","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"7TBMW4D7UA2FJHQ6","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"7TBMW4D7","created_at":"2026-06-03T01:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7TBMW4D7UA2FJHQ6BVWUIAO222","target":"record","payload":{"canonical_record":{"source":{"id":"2605.03299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T02:40:39Z","cross_cats_sorted":[],"title_canon_sha256":"7898ab9d9a558b58cd4fec01e4504898656b4ffbe6b7a9dcbcac43bdb78bc117","abstract_canon_sha256":"48b9122eecbe939d894b2eb48e335253c8899e151e935b32dae8b0de78d92acc"},"schema_version":"1.0"},"canonical_sha256":"fcc2cb707fa034549e1e0d6d4401dad6b8e28ae25d99d55aa23d78f599ecc02c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:14.429450Z","signature_b64":"aq3m6KqfJuGNIWxzYV6jxLrX9LTcYuBkBQTXKSfaUdGTJyxjD58HlwLb4x6SEC/ZDieHK1BO3Wm3TtCE/0IQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc2cb707fa034549e1e0d6d4401dad6b8e28ae25d99d55aa23d78f599ecc02c","last_reissued_at":"2026-06-03T01:05:14.429059Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:14.429059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.03299","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":"2026-06-03T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPPAaWFsFaWRwUrL+nK0g9xs61lBW3/ItXJKzV3KgmBiY3K3ohFyaTXSuKZCmHF9vEl4Wfg+gZQiD96n9grtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T13:51:25.291519Z"},"content_sha256":"3857fd10834dc4beb691e773f8e82860b5399cb98a9be5c710f9574e97900a06","schema_version":"1.0","event_id":"sha256:3857fd10834dc4beb691e773f8e82860b5399cb98a9be5c710f9574e97900a06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7TBMW4D7UA2FJHQ6BVWUIAO222","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinh Viet Sang, Linh Ngo Van, Minh Chu Xuan, Nguyen Thi Ngoc Diep, Tien-Phat Nguyen, Trung Le","submitted_at":"2026-05-05T02:40:39Z","abstract_excerpt":"Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve interpretability but are costly, document-level, and prone to hallucination, with prior white-box approaches requiring inaccessible token probabilities. We propose LLM-XTM, a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification, enabling black-box, stable, and scalable enhancement of cross-lingual topic models."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM refinements remain stable and non-hallucinated when used in a black-box manner and that self-consistency scores reliably indicate topic quality without introducing new biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM-XTM integrates LLM-guided topic refinement with self-consistency uncertainty quantification to improve coherence and alignment in cross-lingual topic models while reducing dependence on bilingual resources and repeated LLM calls.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8fd50775ea5f7beb6ea4c891d9b787d10fcb2a217d2a3d7d59572a4d2aad1f76"},"source":{"id":"2605.03299","kind":"arxiv","version":2},"verdict":{"id":"663a35e7-e734-49bc-a2b1-66a6b52e0e43","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:55:18.047888Z","strongest_claim":"Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.","one_line_summary":"LLM-XTM integrates LLM-guided topic refinement with self-consistency uncertainty quantification to improve coherence and alignment in cross-lingual topic models while reducing dependence on bilingual resources and repeated LLM calls.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM refinements remain stable and non-hallucinated when used in a black-box manner and that self-consistency scores reliably indicate topic quality without introducing new biases.","pith_extraction_headline":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03299/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T14:34:19.584112Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T01:31:21.520561Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:29:23.402950Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3305ec2c843b8199caeaf609da05f5846baf0b4060d031145fa4ca81fd432d98"},"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":"663a35e7-e734-49bc-a2b1-66a6b52e0e43"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeaxJ1a3P6YBaN/AC3QSLFNSZnFaPRPAdFekdwrlat7UVwpbSa8iZ21SLREHBpmDes8BZrYs9FJcCkt9oJimCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T13:51:25.292516Z"},"content_sha256":"d675fedb285a4ef0a75cb40e6cb9394a2dfc1c4b59d4fe5cfff131354195a24c","schema_version":"1.0","event_id":"sha256:d675fedb285a4ef0a75cb40e6cb9394a2dfc1c4b59d4fe5cfff131354195a24c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/bundle.json","state_url":"https://pith.science/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/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":"2026-06-07T13:51:25Z","links":{"resolver":"https://pith.science/pith/7TBMW4D7UA2FJHQ6BVWUIAO222","bundle":"https://pith.science/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/bundle.json","state":"https://pith.science/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TBMW4D7UA2FJHQ6BVWUIAO222/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7TBMW4D7UA2FJHQ6BVWUIAO222","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":"48b9122eecbe939d894b2eb48e335253c8899e151e935b32dae8b0de78d92acc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T02:40:39Z","title_canon_sha256":"7898ab9d9a558b58cd4fec01e4504898656b4ffbe6b7a9dcbcac43bdb78bc117"},"schema_version":"1.0","source":{"id":"2605.03299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03299","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03299v2","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03299","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"7TBMW4D7UA2F","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"7TBMW4D7UA2FJHQ6","created_at":"2026-06-03T01:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"7TBMW4D7","created_at":"2026-06-03T01:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:d675fedb285a4ef0a75cb40e6cb9394a2dfc1c4b59d4fe5cfff131354195a24c","target":"graph","created_at":"2026-06-03T01:05:14Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM refinements remain stable and non-hallucinated when used in a black-box manner and that self-consistency scores reliably indicate topic quality without introducing new biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LLM-XTM integrates LLM-guided topic refinement with self-consistency uncertainty quantification to improve coherence and alignment in cross-lingual topic models while reducing dependence on bilingual resources and repeated LLM calls."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment."}],"snapshot_sha256":"8fd50775ea5f7beb6ea4c891d9b787d10fcb2a217d2a3d7d59572a4d2aad1f76"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T14:34:19.584112Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T01:31:21.520561Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:29:23.402950Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.03299/integrity.json","findings":[],"snapshot_sha256":"3305ec2c843b8199caeaf609da05f5846baf0b4060d031145fa4ca81fd432d98","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve interpretability but are costly, document-level, and prone to hallucination, with prior white-box approaches requiring inaccessible token probabilities. We propose LLM-XTM, a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification, enabling black-box, stable, and scalable enhancement of cross-lingual topic models.","authors_text":"Dinh Viet Sang, Linh Ngo Van, Minh Chu Xuan, Nguyen Thi Ngoc Diep, Tien-Phat Nguyen, Trung Le","cross_cats":[],"headline":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T02:40:39Z","title":"LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03299","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T16:55:18.047888Z","id":"663a35e7-e734-49bc-a2b1-66a6b52e0e43","model_set":{"reader":"grok-4.3"},"one_line_summary":"LLM-XTM integrates LLM-guided topic refinement with self-consistency uncertainty quantification to improve coherence and alignment in cross-lingual topic models while reducing dependence on bilingual resources and repeated LLM calls.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LLM-XTM refines cross-lingual topics using black-box LLM guidance and self-consistency scoring to gain coherence and alignment.","strongest_claim":"Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.","weakest_assumption":"That LLM refinements remain stable and non-hallucinated when used in a black-box manner and that self-consistency scores reliably indicate topic quality without introducing new biases."}},"verdict_id":"663a35e7-e734-49bc-a2b1-66a6b52e0e43"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3857fd10834dc4beb691e773f8e82860b5399cb98a9be5c710f9574e97900a06","target":"record","created_at":"2026-06-03T01:05:14Z","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":"48b9122eecbe939d894b2eb48e335253c8899e151e935b32dae8b0de78d92acc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T02:40:39Z","title_canon_sha256":"7898ab9d9a558b58cd4fec01e4504898656b4ffbe6b7a9dcbcac43bdb78bc117"},"schema_version":"1.0","source":{"id":"2605.03299","kind":"arxiv","version":2}},"canonical_sha256":"fcc2cb707fa034549e1e0d6d4401dad6b8e28ae25d99d55aa23d78f599ecc02c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcc2cb707fa034549e1e0d6d4401dad6b8e28ae25d99d55aa23d78f599ecc02c","first_computed_at":"2026-06-03T01:05:14.429059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:14.429059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aq3m6KqfJuGNIWxzYV6jxLrX9LTcYuBkBQTXKSfaUdGTJyxjD58HlwLb4x6SEC/ZDieHK1BO3Wm3TtCE/0IQBg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:14.429450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3857fd10834dc4beb691e773f8e82860b5399cb98a9be5c710f9574e97900a06","sha256:d675fedb285a4ef0a75cb40e6cb9394a2dfc1c4b59d4fe5cfff131354195a24c"],"state_sha256":"29493eab61db7aef3f6ecb6f59e72cf7a1733a5743fc78b731d9840f0e255ddc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kERe6zlem8BW4QRVCUB3Tt2RGciunkaAv5EGYF5rJFii73/EINaqcTfIKHfYvxxti+Lc0e7M7AcoQC9tvceKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T13:51:25.296929Z","bundle_sha256":"b62edd7dc30c269ecf325f14b080fe1b07bc13472c0ae8d1d266e0f65f1a1327"}}