{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S7N7VHINESDF6MRHDZ22HL7HW2","short_pith_number":"pith:S7N7VHIN","canonical_record":{"source":{"id":"2508.15612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T14:36:53Z","cross_cats_sorted":[],"title_canon_sha256":"708c3703ad5c18e16d99cf165e5bf143f6ee6720d1611578a256da5127ca2e83","abstract_canon_sha256":"3ab87e88aa94f01e90415bcbecc36bd902e14b5b8f911949f72cf683a92a0319"},"schema_version":"1.0"},"canonical_sha256":"97dbfa9d0d24865f32271e75a3afe7b6a00759f74d668c701af8ec9879c1a29c","source":{"kind":"arxiv","id":"2508.15612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15612","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15612v1","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15612","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"S7N7VHINESDF","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"S7N7VHINESDF6MRH","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"S7N7VHIN","created_at":"2026-07-05T11:57:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S7N7VHINESDF6MRHDZ22HL7HW2","target":"record","payload":{"canonical_record":{"source":{"id":"2508.15612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T14:36:53Z","cross_cats_sorted":[],"title_canon_sha256":"708c3703ad5c18e16d99cf165e5bf143f6ee6720d1611578a256da5127ca2e83","abstract_canon_sha256":"3ab87e88aa94f01e90415bcbecc36bd902e14b5b8f911949f72cf683a92a0319"},"schema_version":"1.0"},"canonical_sha256":"97dbfa9d0d24865f32271e75a3afe7b6a00759f74d668c701af8ec9879c1a29c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:15.421077Z","signature_b64":"tBe0lvdQPXNHekbqDMXaSBwoVBpfWP/GNn11nqn0fTkJD1KYmrNJ4+vk42pjttP8lIzokmJ90f/q5WA7pzCFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97dbfa9d0d24865f32271e75a3afe7b6a00759f74d668c701af8ec9879c1a29c","last_reissued_at":"2026-07-05T11:57:15.420718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:15.420718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.15612","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":"2026-07-05T11:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+Ml6bpGm2KwBy0fm4YlMlMB1rXTtKker4TYygR44k8aJfPr+9fLQFA+QoKmXleDA/UsU7664C3OhTsizGG2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:05:34.313919Z"},"content_sha256":"67da3710625e3c331f17d23a62b0018e57de47c6a599d9aaf6c3c925e4e4c9d1","schema_version":"1.0","event_id":"sha256:67da3710625e3c331f17d23a62b0018e57de47c6a599d9aaf6c3c925e4e4c9d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S7N7VHINESDF6MRHDZ22HL7HW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Neural Topic Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charu Karakkaparambil James, Marius Kloft, Sophie Fellenz, Waleed Mustafa","submitted_at":"2025-08-21T14:36:53Z","abstract_excerpt":"In continual learning, our aim is to learn a new task without forgetting what was learned previously. In topic models, this translates to learning new topic models without forgetting previously learned topics. Previous work either considered Dynamic Topic Models (DTMs), which learn the evolution of topics based on the entire training corpus at once, or Online Topic Models, which are updated continuously based on new data but do not have long-term memory. To fill this gap, we propose the Continual Neural Topic Model (CoNTM), which continuously learns topic models at subsequent time steps withou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15612","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/2508.15612/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":"2026-07-05T11:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGZMDAYG/LBRc4DItT69oc/deiHdQoR6gLMq4tQtzpy34hwOA6P3BULOHz878e8UcCUYggBtIOSFxdC57psgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:05:34.314302Z"},"content_sha256":"c19c2edd70a5185f80ab5846f3a8384a6ae3b53618d61c6cd7db1369977e8b1e","schema_version":"1.0","event_id":"sha256:c19c2edd70a5185f80ab5846f3a8384a6ae3b53618d61c6cd7db1369977e8b1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7N7VHINESDF6MRHDZ22HL7HW2/bundle.json","state_url":"https://pith.science/pith/S7N7VHINESDF6MRHDZ22HL7HW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7N7VHINESDF6MRHDZ22HL7HW2/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":"2026-07-23T22:05:34Z","links":{"resolver":"https://pith.science/pith/S7N7VHINESDF6MRHDZ22HL7HW2","bundle":"https://pith.science/pith/S7N7VHINESDF6MRHDZ22HL7HW2/bundle.json","state":"https://pith.science/pith/S7N7VHINESDF6MRHDZ22HL7HW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7N7VHINESDF6MRHDZ22HL7HW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S7N7VHINESDF6MRHDZ22HL7HW2","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":"3ab87e88aa94f01e90415bcbecc36bd902e14b5b8f911949f72cf683a92a0319","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T14:36:53Z","title_canon_sha256":"708c3703ad5c18e16d99cf165e5bf143f6ee6720d1611578a256da5127ca2e83"},"schema_version":"1.0","source":{"id":"2508.15612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15612","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15612v1","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15612","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"S7N7VHINESDF","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"S7N7VHINESDF6MRH","created_at":"2026-07-05T11:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"S7N7VHIN","created_at":"2026-07-05T11:57:15Z"}],"graph_snapshots":[{"event_id":"sha256:c19c2edd70a5185f80ab5846f3a8384a6ae3b53618d61c6cd7db1369977e8b1e","target":"graph","created_at":"2026-07-05T11:57:15Z","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/2508.15612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In continual learning, our aim is to learn a new task without forgetting what was learned previously. In topic models, this translates to learning new topic models without forgetting previously learned topics. Previous work either considered Dynamic Topic Models (DTMs), which learn the evolution of topics based on the entire training corpus at once, or Online Topic Models, which are updated continuously based on new data but do not have long-term memory. To fill this gap, we propose the Continual Neural Topic Model (CoNTM), which continuously learns topic models at subsequent time steps withou","authors_text":"Charu Karakkaparambil James, Marius Kloft, Sophie Fellenz, Waleed Mustafa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T14:36:53Z","title":"Continual Neural Topic Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15612","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":"sha256:67da3710625e3c331f17d23a62b0018e57de47c6a599d9aaf6c3c925e4e4c9d1","target":"record","created_at":"2026-07-05T11:57:15Z","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":"3ab87e88aa94f01e90415bcbecc36bd902e14b5b8f911949f72cf683a92a0319","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T14:36:53Z","title_canon_sha256":"708c3703ad5c18e16d99cf165e5bf143f6ee6720d1611578a256da5127ca2e83"},"schema_version":"1.0","source":{"id":"2508.15612","kind":"arxiv","version":1}},"canonical_sha256":"97dbfa9d0d24865f32271e75a3afe7b6a00759f74d668c701af8ec9879c1a29c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97dbfa9d0d24865f32271e75a3afe7b6a00759f74d668c701af8ec9879c1a29c","first_computed_at":"2026-07-05T11:57:15.420718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:15.420718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tBe0lvdQPXNHekbqDMXaSBwoVBpfWP/GNn11nqn0fTkJD1KYmrNJ4+vk42pjttP8lIzokmJ90f/q5WA7pzCFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:15.421077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67da3710625e3c331f17d23a62b0018e57de47c6a599d9aaf6c3c925e4e4c9d1","sha256:c19c2edd70a5185f80ab5846f3a8384a6ae3b53618d61c6cd7db1369977e8b1e"],"state_sha256":"62a53cb191c94bf0dc6bc2cf2c732bf5542e6ca8004f86a06e6588a96ef0867b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WwtpvnlDf0RsL+J0Z4tVYHHQ1Qk3gscsNUCAiaMGQeNz4zknaWw1WpBoMk2agDxVtGG8q0FkLZwwmkwviDp4CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T22:05:34.316889Z","bundle_sha256":"269e62170196d795d6210a7acb6ca219ae0b967fb0637aeee128631321bf0e80"}}