{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VDFFUCT3GXXIZHCOXCBX5E5GZE","short_pith_number":"pith:VDFFUCT3","schema_version":"1.0","canonical_sha256":"a8ca5a0a7b35ee8c9c4eb8837e93a6c913406007bc5f7340c994a1069b0083fa","source":{"kind":"arxiv","id":"2310.10567","version":2},"attestation_state":"computed","paper":{"title":"RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huawei Shen, Jingcheng Deng, Liang Pang, Xueqi Cheng","submitted_at":"2023-10-16T16:42:01Z","abstract_excerpt":"Retrieval-augmented language models show promise in addressing issues like outdated information and hallucinations in language models (LMs). However, current research faces two main problems: 1) determining what information to retrieve, and 2) effectively combining retrieved information during generation. We argue that valuable retrieved information should not only be related to the current source text but also consider the future target text, given the nature of LMs that model future tokens. Moreover, we propose that aggregation using latent variables derived from a compact latent space is mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.10567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T16:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"bacc115b2e1849cb853fa12904ec137534b496a7071ab5de734410834794f826","abstract_canon_sha256":"e233699d94923a5279389402848390c05cd0cc635afb5f8e1b5578997e2d34c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:01.200263Z","signature_b64":"+UcjL4AiDH8B/fmPKpj3r6VqIus0OnNbrOybqDm6xIOIeGFEz30nfsjLhrmZq3At5ze+46jwIFV78nPnW+ekAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8ca5a0a7b35ee8c9c4eb8837e93a6c913406007bc5f7340c994a1069b0083fa","last_reissued_at":"2026-07-05T07:04:01.199752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:01.199752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huawei Shen, Jingcheng Deng, Liang Pang, Xueqi Cheng","submitted_at":"2023-10-16T16:42:01Z","abstract_excerpt":"Retrieval-augmented language models show promise in addressing issues like outdated information and hallucinations in language models (LMs). However, current research faces two main problems: 1) determining what information to retrieve, and 2) effectively combining retrieved information during generation. We argue that valuable retrieved information should not only be related to the current source text but also consider the future target text, given the nature of LMs that model future tokens. Moreover, we propose that aggregation using latent variables derived from a compact latent space is mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10567","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/2310.10567/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.10567","created_at":"2026-07-05T07:04:01.199818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10567v2","created_at":"2026-07-05T07:04:01.199818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10567","created_at":"2026-07-05T07:04:01.199818+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDFFUCT3GXXI","created_at":"2026-07-05T07:04:01.199818+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDFFUCT3GXXIZHCO","created_at":"2026-07-05T07:04:01.199818+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDFFUCT3","created_at":"2026-07-05T07:04:01.199818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08222","citing_title":"Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE","json":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE.json","graph_json":"https://pith.science/api/pith-number/VDFFUCT3GXXIZHCOXCBX5E5GZE/graph.json","events_json":"https://pith.science/api/pith-number/VDFFUCT3GXXIZHCOXCBX5E5GZE/events.json","paper":"https://pith.science/paper/VDFFUCT3"},"agent_actions":{"view_html":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE","download_json":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE.json","view_paper":"https://pith.science/paper/VDFFUCT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10567&json=true","fetch_graph":"https://pith.science/api/pith-number/VDFFUCT3GXXIZHCOXCBX5E5GZE/graph.json","fetch_events":"https://pith.science/api/pith-number/VDFFUCT3GXXIZHCOXCBX5E5GZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE/action/storage_attestation","attest_author":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE/action/author_attestation","sign_citation":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE/action/citation_signature","submit_replication":"https://pith.science/pith/VDFFUCT3GXXIZHCOXCBX5E5GZE/action/replication_record"}},"created_at":"2026-07-05T07:04:01.199818+00:00","updated_at":"2026-07-05T07:04:01.199818+00:00"}