{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G26LJGP2IT6L733M6IZRML6XRH","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":"c7fb8820cd6139316dbac167ab8007113129d769fb3509d626bd5f7007f7f7f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T00:12:04Z","title_canon_sha256":"ff149898a957bb53dd585a0b4390f2cf731b419f71205138e181cc4733f4ff64"},"schema_version":"1.0","source":{"id":"2602.17907","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17907","created_at":"2026-06-04T01:08:45Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17907v2","created_at":"2026-06-04T01:08:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17907","created_at":"2026-06-04T01:08:45Z"},{"alias_kind":"pith_short_12","alias_value":"G26LJGP2IT6L","created_at":"2026-06-04T01:08:45Z"},{"alias_kind":"pith_short_16","alias_value":"G26LJGP2IT6L733M","created_at":"2026-06-04T01:08:45Z"},{"alias_kind":"pith_short_8","alias_value":"G26LJGP2","created_at":"2026-06-04T01:08:45Z"}],"graph_snapshots":[{"event_id":"sha256:15df71e72850d28cc1ba944c6a8d339d49a15e74278053a6821b276441d8f68f","target":"graph","created_at":"2026-06-04T01:08:45Z","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/2602.17907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we introduce a novel topic model training framework by Distilling Soft Labels (DSL) from Language Models (LMs). To construct the contextually enriched reconstruction signals, we project the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary, and train the topic models to reconstruct the soft labels using the LM hidden states. This produces higher-","authors_text":"Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini, Raymond Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T00:12:04Z","title":"DSL-Topic: Improving Topic Modeling by Distilling Soft Labelsfrom Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17907","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:f609b5bfa30db6938895bb0ad22b9a928d49874967f947abce389f129cc8f726","target":"record","created_at":"2026-06-04T01:08:45Z","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":"c7fb8820cd6139316dbac167ab8007113129d769fb3509d626bd5f7007f7f7f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T00:12:04Z","title_canon_sha256":"ff149898a957bb53dd585a0b4390f2cf731b419f71205138e181cc4733f4ff64"},"schema_version":"1.0","source":{"id":"2602.17907","kind":"arxiv","version":2}},"canonical_sha256":"36bcb499fa44fcbfef6cf233162fd789eec07a1c2cc21e7bd7a1fb0ebac326b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36bcb499fa44fcbfef6cf233162fd789eec07a1c2cc21e7bd7a1fb0ebac326b4","first_computed_at":"2026-06-04T01:08:45.801787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:45.801787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6OgYrezsXgKx45LSFlS0S5srt5xR+uupJyURrrFoVkedsLICdqGXzfPgBIXvUc5ktG341G24zhuO9+MgVaq2Dg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:45.802618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17907","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f609b5bfa30db6938895bb0ad22b9a928d49874967f947abce389f129cc8f726","sha256:15df71e72850d28cc1ba944c6a8d339d49a15e74278053a6821b276441d8f68f"],"state_sha256":"375138917b1b73bd06cf34ef0489b987493b2fcc5b9029f4b3161e1ca52f6309"}