{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PZE4K3FWB5C3W3SUEJZGFOX5J6","short_pith_number":"pith:PZE4K3FW","canonical_record":{"source":{"id":"2304.03544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T08:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"d733bdd39cc068d40d14206b8ca8162c76694622c01ca2cfb7aeb5ac08f65dd9","abstract_canon_sha256":"6fd7e53c828ec1d67185962bafafdf6af7384ca83425d8182210034eb522a996"},"schema_version":"1.0"},"canonical_sha256":"7e49c56cb60f45bb6e54227262bafd4f941d7de62089214eec009856cd21aca1","source":{"kind":"arxiv","id":"2304.03544","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03544","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03544v2","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03544","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"PZE4K3FWB5C3","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"PZE4K3FWB5C3W3SU","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"PZE4K3FW","created_at":"2026-07-05T08:01:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PZE4K3FWB5C3W3SUEJZGFOX5J6","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T08:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"d733bdd39cc068d40d14206b8ca8162c76694622c01ca2cfb7aeb5ac08f65dd9","abstract_canon_sha256":"6fd7e53c828ec1d67185962bafafdf6af7384ca83425d8182210034eb522a996"},"schema_version":"1.0"},"canonical_sha256":"7e49c56cb60f45bb6e54227262bafd4f941d7de62089214eec009856cd21aca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:14.196447Z","signature_b64":"QyOQLoA9R1Imhyw17o7EXEO8NKs3m8FX2DD3BzXYV/4cqdMdOxBKzHSoaDlL85NDX088BFJ4xfJaxwbeJ9roAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e49c56cb60f45bb6e54227262bafd4f941d7de62089214eec009856cd21aca1","last_reissued_at":"2026-07-05T08:01:14.195976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:14.195976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03544","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":"2026-07-05T08:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"le9ZEPf5uW7TBi0VMY9Hb+uMzsE2OJIFOaX2cfzt7HK9QN/D1aFI9hZUm7LYTmvmvUnvm067vFZMrYcMUYmmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:05:34.349934Z"},"content_sha256":"90a86cb2aa9691e5bba7d66cd4495339415d9b3f047092042d9ed5d8b4d34ead","schema_version":"1.0","event_id":"sha256:90a86cb2aa9691e5bba7d66cd4495339415d9b3f047092042d9ed5d8b4d34ead"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PZE4K3FWB5C3W3SUEJZGFOX5J6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Chaoqun Liu, Liangming Pan, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","submitted_at":"2023-04-07T08:49:43Z","abstract_excerpt":"Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. However, most existing methods suffer from producing repetitive topics that hinder further analysis and performance decline caused by low-coverage dictionaries. In this paper, we propose the Cross-lingual Topic Modeling with Mutual Information (InfoCTM). Instead of the direct alignment in previous work, we propose a topic alignment with mutual information method. This works as a regularization to properly align topics and prevent degenerate topic representations of words, which mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03544","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/2304.03544/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":"2026-07-05T08:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yer/Nf8glPEnj92B2yq8Q5xnKx8XUGahvSvssXpVf2q1kjFcrhm7oLX/3QCG0Ta5dnmFa4VWQbOFyZD8U6HhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:05:34.350537Z"},"content_sha256":"c5cb0b4a4ad850d063b6a305ea795b9786d1da011cbc01c75e8d4720476e3d35","schema_version":"1.0","event_id":"sha256:c5cb0b4a4ad850d063b6a305ea795b9786d1da011cbc01c75e8d4720476e3d35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/bundle.json","state_url":"https://pith.science/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/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":"2026-08-16T17:05:34Z","links":{"resolver":"https://pith.science/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6","bundle":"https://pith.science/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/bundle.json","state":"https://pith.science/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZE4K3FWB5C3W3SUEJZGFOX5J6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PZE4K3FWB5C3W3SUEJZGFOX5J6","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":"6fd7e53c828ec1d67185962bafafdf6af7384ca83425d8182210034eb522a996","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T08:49:43Z","title_canon_sha256":"d733bdd39cc068d40d14206b8ca8162c76694622c01ca2cfb7aeb5ac08f65dd9"},"schema_version":"1.0","source":{"id":"2304.03544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03544","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03544v2","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03544","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"PZE4K3FWB5C3","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"PZE4K3FWB5C3W3SU","created_at":"2026-07-05T08:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"PZE4K3FW","created_at":"2026-07-05T08:01:14Z"}],"graph_snapshots":[{"event_id":"sha256:c5cb0b4a4ad850d063b6a305ea795b9786d1da011cbc01c75e8d4720476e3d35","target":"graph","created_at":"2026-07-05T08:01:14Z","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/2304.03544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. However, most existing methods suffer from producing repetitive topics that hinder further analysis and performance decline caused by low-coverage dictionaries. In this paper, we propose the Cross-lingual Topic Modeling with Mutual Information (InfoCTM). Instead of the direct alignment in previous work, we propose a topic alignment with mutual information method. This works as a regularization to properly align topics and prevent degenerate topic representations of words, which mi","authors_text":"Anh Tuan Luu, Chaoqun Liu, Liangming Pan, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T08:49:43Z","title":"InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03544","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":"sha256:90a86cb2aa9691e5bba7d66cd4495339415d9b3f047092042d9ed5d8b4d34ead","target":"record","created_at":"2026-07-05T08:01:14Z","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":"6fd7e53c828ec1d67185962bafafdf6af7384ca83425d8182210034eb522a996","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T08:49:43Z","title_canon_sha256":"d733bdd39cc068d40d14206b8ca8162c76694622c01ca2cfb7aeb5ac08f65dd9"},"schema_version":"1.0","source":{"id":"2304.03544","kind":"arxiv","version":2}},"canonical_sha256":"7e49c56cb60f45bb6e54227262bafd4f941d7de62089214eec009856cd21aca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e49c56cb60f45bb6e54227262bafd4f941d7de62089214eec009856cd21aca1","first_computed_at":"2026-07-05T08:01:14.195976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:14.195976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QyOQLoA9R1Imhyw17o7EXEO8NKs3m8FX2DD3BzXYV/4cqdMdOxBKzHSoaDlL85NDX088BFJ4xfJaxwbeJ9roAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:14.196447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a86cb2aa9691e5bba7d66cd4495339415d9b3f047092042d9ed5d8b4d34ead","sha256:c5cb0b4a4ad850d063b6a305ea795b9786d1da011cbc01c75e8d4720476e3d35"],"state_sha256":"a3e066a8ff971edec9fbeefa401bf0e358347e4e4e02a2b2bed426e7ead95c4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPIjc7f1qsnO9duzjyNl/IqU6Qpo+9B4T4eOTkayE7A6UeLarYcnRzfNW0PWck9b8LS7WXBTvi44xictN53bCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T17:05:34.356180Z","bundle_sha256":"71de2bcf4bdc42b0a9fa031b6a197600f9ead02309e5f443b5dc190ccbdbc289"}}