{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4T76F2LUUAIHPXCPXOB4T55IAJ","short_pith_number":"pith:4T76F2LU","canonical_record":{"source":{"id":"2306.04217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","cross_cats_sorted":[],"title_canon_sha256":"a618267b21024e6e93fc84e07966ca5cf10ac0386f3af68f19deaaf39ee56d4e","abstract_canon_sha256":"cacd01747257e1bb2b498e0af96efd33295c649a30d6c557e5006ade579b32c8"},"schema_version":"1.0"},"canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","source":{"kind":"arxiv","id":"2306.04217","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04217","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04217v1","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04217","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"4T76F2LUUAIH","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"4T76F2LUUAIHPXCP","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"4T76F2LU","created_at":"2026-07-05T06:18:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4T76F2LUUAIHPXCPXOB4T55IAJ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","cross_cats_sorted":[],"title_canon_sha256":"a618267b21024e6e93fc84e07966ca5cf10ac0386f3af68f19deaaf39ee56d4e","abstract_canon_sha256":"cacd01747257e1bb2b498e0af96efd33295c649a30d6c557e5006ade579b32c8"},"schema_version":"1.0"},"canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:27.219018Z","signature_b64":"UVmuWyLZ3XWTy/E+P8Ofkehrd6uf5BECgGZUja0U4GIIjoZQf5sNMDLkIjGSI7rcgoyc4fD4KiN8Lw5ofkm0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","last_reissued_at":"2026-07-05T06:18:27.218494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:27.218494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04217","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":"2026-07-05T06:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oB/IY/9FfVQ2mRDloPL7wwgKYPBobRi2ASvlabqR5Ip2wDMDoV4btdJI+BqQxzzCoi9cD+/wMOF41aTPzVBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:05:22.825634Z"},"content_sha256":"5b8b001fd42d0ce48a91961a356e2849b3f014e321a202320a16f30ff2590f00","schema_version":"1.0","event_id":"sha256:5b8b001fd42d0ce48a91961a356e2849b3f014e321a202320a16f30ff2590f00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4T76F2LUUAIHPXCPXOB4T55IAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Neural Topic Modeling with Embedding Clustering Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","submitted_at":"2023-06-07T07:45:38Z","abstract_excerpt":"Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semantically collapse towards each other, leading to highly repetitive topics, insufficient topic discovery, and damaged model interpretability. In this paper, we propose a new neural topic model, Embedding Clustering Regularization Topic Model (ECRTM). Besides the existing reconstruction error, we propose a novel Embedding Clustering Regularization (ECR), which forces each topic embedding to be the center of a separately "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04217","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/2306.04217/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":"2026-07-05T06:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKphBel9B+MrNBhMaGzs944cLNtR/yjprWIh/EW1f/H3ggQM+MbxUSKPppev14lRDv8yYyA6BY2fPCrO4xt6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:05:22.826609Z"},"content_sha256":"ba05090fba61fdf1554baaa083a38b621c3d3840c32b59b1c7bb9238a92aa87f","schema_version":"1.0","event_id":"sha256:ba05090fba61fdf1554baaa083a38b621c3d3840c32b59b1c7bb9238a92aa87f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/bundle.json","state_url":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/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":"2026-08-05T09:05:22Z","links":{"resolver":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ","bundle":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/bundle.json","state":"https://pith.science/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4T76F2LUUAIHPXCPXOB4T55IAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4T76F2LUUAIHPXCPXOB4T55IAJ","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":"cacd01747257e1bb2b498e0af96efd33295c649a30d6c557e5006ade579b32c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","title_canon_sha256":"a618267b21024e6e93fc84e07966ca5cf10ac0386f3af68f19deaaf39ee56d4e"},"schema_version":"1.0","source":{"id":"2306.04217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04217","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04217v1","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04217","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"4T76F2LUUAIH","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"4T76F2LUUAIHPXCP","created_at":"2026-07-05T06:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"4T76F2LU","created_at":"2026-07-05T06:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:ba05090fba61fdf1554baaa083a38b621c3d3840c32b59b1c7bb9238a92aa87f","target":"graph","created_at":"2026-07-05T06:18:27Z","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/2306.04217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semantically collapse towards each other, leading to highly repetitive topics, insufficient topic discovery, and damaged model interpretability. In this paper, we propose a new neural topic model, Embedding Clustering Regularization Topic Model (ECRTM). Besides the existing reconstruction error, we propose a novel Embedding Clustering Regularization (ECR), which forces each topic embedding to be the center of a separately ","authors_text":"Anh Tuan Luu, Thong Nguyen, Xiaobao Wu, Xinshuai Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","title":"Effective Neural Topic Modeling with Embedding Clustering Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04217","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":"sha256:5b8b001fd42d0ce48a91961a356e2849b3f014e321a202320a16f30ff2590f00","target":"record","created_at":"2026-07-05T06:18:27Z","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":"cacd01747257e1bb2b498e0af96efd33295c649a30d6c557e5006ade579b32c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T07:45:38Z","title_canon_sha256":"a618267b21024e6e93fc84e07966ca5cf10ac0386f3af68f19deaaf39ee56d4e"},"schema_version":"1.0","source":{"id":"2306.04217","kind":"arxiv","version":1}},"canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4ffe2e974a01077dc4fbb83c9f7a802457ece31ec318569079e153a8e1cbd4f","first_computed_at":"2026-07-05T06:18:27.218494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:27.218494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UVmuWyLZ3XWTy/E+P8Ofkehrd6uf5BECgGZUja0U4GIIjoZQf5sNMDLkIjGSI7rcgoyc4fD4KiN8Lw5ofkm0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:27.219018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b8b001fd42d0ce48a91961a356e2849b3f014e321a202320a16f30ff2590f00","sha256:ba05090fba61fdf1554baaa083a38b621c3d3840c32b59b1c7bb9238a92aa87f"],"state_sha256":"fbf69a7402dce7836e1cf7330917050d88b69e54a95148bea52222b347df9eb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23aVGRKDbDuqu3LGyhDd3mWcUj+wX8q8qit+GOtz/tstAV3ZOhCMUqAL52Kus1UKQao94YyxobyFQZDuaZrDBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:05:22.831710Z","bundle_sha256":"ed54b0943df677ae5c8e41b2f56308ea80218c1dbd6d4e68a7cc7222f4443c26"}}