{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RI6KHCOABS5DOHFTE3FIJIHXSH","short_pith_number":"pith:RI6KHCOA","canonical_record":{"source":{"id":"2508.07654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-11T06:06:26Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d86b874061649503291a21f143b718f7b2af664042bfe80fcbd5e8f641db7e7a","abstract_canon_sha256":"480548fc86aefba8732e22fae2cd2e1e261871453c8ea1e60d96eccc4f6c3f78"},"schema_version":"1.0"},"canonical_sha256":"8a3ca389c00cba371cb326ca84a0f791fb7c5c1fc04ca0f9b91d5c216eb003ca","source":{"kind":"arxiv","id":"2508.07654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07654","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07654v1","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07654","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"RI6KHCOABS5D","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"RI6KHCOABS5DOHFT","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"RI6KHCOA","created_at":"2026-07-05T11:51:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RI6KHCOABS5DOHFTE3FIJIHXSH","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-11T06:06:26Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d86b874061649503291a21f143b718f7b2af664042bfe80fcbd5e8f641db7e7a","abstract_canon_sha256":"480548fc86aefba8732e22fae2cd2e1e261871453c8ea1e60d96eccc4f6c3f78"},"schema_version":"1.0"},"canonical_sha256":"8a3ca389c00cba371cb326ca84a0f791fb7c5c1fc04ca0f9b91d5c216eb003ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:49.888343Z","signature_b64":"G5uq5DTCQEvq+UK7QRn8Pg/zMxhusK6Kxt127P698S2q9BIgsO0MCOSyVYkkM39HbmFIIKUAu6b7nqKtEdAiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a3ca389c00cba371cb326ca84a0f791fb7c5c1fc04ca0f9b91d5c216eb003ca","last_reissued_at":"2026-07-05T11:51:49.887794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:49.887794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07654","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":"2026-07-05T11:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kcmyr6Cm1ymYLGOHfMoLwRM+SAp7nyaxb4IRIMh1KJ7FFH6ZePcBKnznv5BBsECsYJMz2Xt0oSPuZ6ponj8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:39:15.592752Z"},"content_sha256":"cf52d533c4a3566e23cef7f5676fd6f1e613438a7e37d1c6bb0f5aca19821e11","schema_version":"1.0","event_id":"sha256:cf52d533c4a3566e23cef7f5676fd6f1e613438a7e37d1c6bb0f5aca19821e11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RI6KHCOABS5DOHFTE3FIJIHXSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLego: Interactive and Scalable Topic Exploration Through Model Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Fei Ye, Jiapan Liu, Weirao Wang, X. Sean Wang, Yinan Jing, Zhenying He","submitted_at":"2025-08-11T06:06:26Z","abstract_excerpt":"With massive texts on social media, users and analysts often rely on topic modeling techniques to quickly extract key themes and gain insights. Traditional topic modeling techniques, such as Latent Dirichlet Allocation (LDA), provide valuable insights but are computationally expensive, making them impractical for real-time data analysis. Although recent advances in distributed training and fast sampling methods have improved efficiency, real-time topic exploration remains a significant challenge. In this paper, we present MLego, an interactive query framework designed to support real-time topi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07654","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/2508.07654/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":"2026-07-05T11:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIcTcqqcC8NXux15jNgwIB/KZOdXWQV13w6Q9t6DM8LLx1526m06jQTwopjRNJd6ubnnyzx0fwT2KDj7cDCGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:39:15.593254Z"},"content_sha256":"aa9e453049c0c29dfdee61d42cd6a40130fb1df7e7ed00e4dbf4577d3a7bad7b","schema_version":"1.0","event_id":"sha256:aa9e453049c0c29dfdee61d42cd6a40130fb1df7e7ed00e4dbf4577d3a7bad7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/bundle.json","state_url":"https://pith.science/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/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":"2026-08-22T03:39:15Z","links":{"resolver":"https://pith.science/pith/RI6KHCOABS5DOHFTE3FIJIHXSH","bundle":"https://pith.science/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/bundle.json","state":"https://pith.science/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RI6KHCOABS5DOHFTE3FIJIHXSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RI6KHCOABS5DOHFTE3FIJIHXSH","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":"480548fc86aefba8732e22fae2cd2e1e261871453c8ea1e60d96eccc4f6c3f78","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-11T06:06:26Z","title_canon_sha256":"d86b874061649503291a21f143b718f7b2af664042bfe80fcbd5e8f641db7e7a"},"schema_version":"1.0","source":{"id":"2508.07654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07654","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07654v1","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07654","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"RI6KHCOABS5D","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"RI6KHCOABS5DOHFT","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"RI6KHCOA","created_at":"2026-07-05T11:51:49Z"}],"graph_snapshots":[{"event_id":"sha256:aa9e453049c0c29dfdee61d42cd6a40130fb1df7e7ed00e4dbf4577d3a7bad7b","target":"graph","created_at":"2026-07-05T11:51:49Z","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/2508.07654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With massive texts on social media, users and analysts often rely on topic modeling techniques to quickly extract key themes and gain insights. Traditional topic modeling techniques, such as Latent Dirichlet Allocation (LDA), provide valuable insights but are computationally expensive, making them impractical for real-time data analysis. Although recent advances in distributed training and fast sampling methods have improved efficiency, real-time topic exploration remains a significant challenge. In this paper, we present MLego, an interactive query framework designed to support real-time topi","authors_text":"Fei Ye, Jiapan Liu, Weirao Wang, X. Sean Wang, Yinan Jing, Zhenying He","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-11T06:06:26Z","title":"MLego: Interactive and Scalable Topic Exploration Through Model Reuse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07654","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:cf52d533c4a3566e23cef7f5676fd6f1e613438a7e37d1c6bb0f5aca19821e11","target":"record","created_at":"2026-07-05T11:51:49Z","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":"480548fc86aefba8732e22fae2cd2e1e261871453c8ea1e60d96eccc4f6c3f78","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-11T06:06:26Z","title_canon_sha256":"d86b874061649503291a21f143b718f7b2af664042bfe80fcbd5e8f641db7e7a"},"schema_version":"1.0","source":{"id":"2508.07654","kind":"arxiv","version":1}},"canonical_sha256":"8a3ca389c00cba371cb326ca84a0f791fb7c5c1fc04ca0f9b91d5c216eb003ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a3ca389c00cba371cb326ca84a0f791fb7c5c1fc04ca0f9b91d5c216eb003ca","first_computed_at":"2026-07-05T11:51:49.887794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:49.887794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G5uq5DTCQEvq+UK7QRn8Pg/zMxhusK6Kxt127P698S2q9BIgsO0MCOSyVYkkM39HbmFIIKUAu6b7nqKtEdAiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:49.888343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf52d533c4a3566e23cef7f5676fd6f1e613438a7e37d1c6bb0f5aca19821e11","sha256:aa9e453049c0c29dfdee61d42cd6a40130fb1df7e7ed00e4dbf4577d3a7bad7b"],"state_sha256":"81848a96d3ea50935d50bee294e56bb730262ef1a66d0990e9b798e677e3d28e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eJTa1JPcxkT18MSlYYbBTubWVXWd/8TEr5lU+5MXjTtNz0W3SxExyLInTrXypYjG1jE+4qQaIXsAgN6gsp+PAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:39:15.598521Z","bundle_sha256":"3b49fbb626d67c3b2bc25b4231f5772c5d39d96ac8d5dd129155dff02be6781b"}}