{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ACESX7JKUFXRAJF3PLEALWXLKO","short_pith_number":"pith:ACESX7JK","canonical_record":{"source":{"id":"2603.10619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-11T10:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"03e0480765aab6c0e2b9e5909d30706dc815f50517b3eabf3dbcffefbc56215e","abstract_canon_sha256":"dc80b173f199f3a03c77764ae04cdf7905c3b8cbecc64a14f3959af404d822ed"},"schema_version":"1.0"},"canonical_sha256":"00892bfd2aa16f1024bb7ac805daeb53a1b9d9dc14a355f88bf202f65d837411","source":{"kind":"arxiv","id":"2603.10619","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10619","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10619v2","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10619","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"ACESX7JKUFXR","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"ACESX7JKUFXRAJF3","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"ACESX7JK","created_at":"2026-06-02T02:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ACESX7JKUFXRAJF3PLEALWXLKO","target":"record","payload":{"canonical_record":{"source":{"id":"2603.10619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-11T10:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"03e0480765aab6c0e2b9e5909d30706dc815f50517b3eabf3dbcffefbc56215e","abstract_canon_sha256":"dc80b173f199f3a03c77764ae04cdf7905c3b8cbecc64a14f3959af404d822ed"},"schema_version":"1.0"},"canonical_sha256":"00892bfd2aa16f1024bb7ac805daeb53a1b9d9dc14a355f88bf202f65d837411","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:52.246060Z","signature_b64":"cgTAGQv0E10/cUzoZeBanI6rgxZXswqCgQ+3x2PR8l/4G4p10JHt16wuTJR5xyQnVd5YMp2ztZc+hNJ1AR/3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00892bfd2aa16f1024bb7ac805daeb53a1b9d9dc14a355f88bf202f65d837411","last_reissued_at":"2026-06-02T02:04:52.245561Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:52.245561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.10619","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tvTpKIUojLSSt0sMx9Eq7AH8mjv97IERsWmtttUwnsRVxVKahmmxWkf3AbryoKmniKgC3KfYd4N7ysBBXq1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T12:44:50.021099Z"},"content_sha256":"e003533ad90c05d3a47245916f70af5142ccddf8db050313e454d462890f7167","schema_version":"1.0","event_id":"sha256:e003533ad90c05d3a47245916f70af5142ccddf8db050313e454d462890f7167"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ACESX7JKUFXRAJF3PLEALWXLKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Similarity and Relatedness in Topic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanlin Xiao, Mauricio A. \\'Alvarez, Rainer Breitling, Yang Wang","submitted_at":"2026-03-11T10:27:43Z","abstract_excerpt":"The recent success of large pre-trained language models (PLMs) has motivated their integration into topic modeling. However, PLM-augmented topic models differ from classical co-occurrence models such as Latent Dirichlet Allocation (LDA) not only in performance, but also in the type of semantic structure they capture. We formalize this distinction along two psycholinguistic axes: thematic relatedness (dog/bone) and taxonomic similarity (dog/wolf). To measure both axes over topic words, we construct a large synthetic benchmark of word pairs using LLM-based annotation and train a neural scorer on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10619","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/2603.10619/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":"2026-06-02T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9/6Lb9XvrBQc3mWaQF7p1Dw3fI+PCH+8OsQirI3wWyPfYcMAZ0p5jHTnmfD0ovbC3sVVrZStny2UFqCBgWPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T12:44:50.021491Z"},"content_sha256":"9762d10455218e8a72623c9d1dbd63241869d9e4ac5851614d6e0c7562d4c558","schema_version":"1.0","event_id":"sha256:9762d10455218e8a72623c9d1dbd63241869d9e4ac5851614d6e0c7562d4c558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACESX7JKUFXRAJF3PLEALWXLKO/bundle.json","state_url":"https://pith.science/pith/ACESX7JKUFXRAJF3PLEALWXLKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACESX7JKUFXRAJF3PLEALWXLKO/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":"2026-06-26T12:44:50Z","links":{"resolver":"https://pith.science/pith/ACESX7JKUFXRAJF3PLEALWXLKO","bundle":"https://pith.science/pith/ACESX7JKUFXRAJF3PLEALWXLKO/bundle.json","state":"https://pith.science/pith/ACESX7JKUFXRAJF3PLEALWXLKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACESX7JKUFXRAJF3PLEALWXLKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ACESX7JKUFXRAJF3PLEALWXLKO","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":"dc80b173f199f3a03c77764ae04cdf7905c3b8cbecc64a14f3959af404d822ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-11T10:27:43Z","title_canon_sha256":"03e0480765aab6c0e2b9e5909d30706dc815f50517b3eabf3dbcffefbc56215e"},"schema_version":"1.0","source":{"id":"2603.10619","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10619","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10619v2","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10619","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"ACESX7JKUFXR","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"ACESX7JKUFXRAJF3","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"ACESX7JK","created_at":"2026-06-02T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:9762d10455218e8a72623c9d1dbd63241869d9e4ac5851614d6e0c7562d4c558","target":"graph","created_at":"2026-06-02T02:04:52Z","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/2603.10619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of large pre-trained language models (PLMs) has motivated their integration into topic modeling. However, PLM-augmented topic models differ from classical co-occurrence models such as Latent Dirichlet Allocation (LDA) not only in performance, but also in the type of semantic structure they capture. We formalize this distinction along two psycholinguistic axes: thematic relatedness (dog/bone) and taxonomic similarity (dog/wolf). To measure both axes over topic words, we construct a large synthetic benchmark of word pairs using LLM-based annotation and train a neural scorer on","authors_text":"Hanlin Xiao, Mauricio A. \\'Alvarez, Rainer Breitling, Yang Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-11T10:27:43Z","title":"Disentangling Similarity and Relatedness in Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10619","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:e003533ad90c05d3a47245916f70af5142ccddf8db050313e454d462890f7167","target":"record","created_at":"2026-06-02T02:04:52Z","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":"dc80b173f199f3a03c77764ae04cdf7905c3b8cbecc64a14f3959af404d822ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-11T10:27:43Z","title_canon_sha256":"03e0480765aab6c0e2b9e5909d30706dc815f50517b3eabf3dbcffefbc56215e"},"schema_version":"1.0","source":{"id":"2603.10619","kind":"arxiv","version":2}},"canonical_sha256":"00892bfd2aa16f1024bb7ac805daeb53a1b9d9dc14a355f88bf202f65d837411","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00892bfd2aa16f1024bb7ac805daeb53a1b9d9dc14a355f88bf202f65d837411","first_computed_at":"2026-06-02T02:04:52.245561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:52.245561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgTAGQv0E10/cUzoZeBanI6rgxZXswqCgQ+3x2PR8l/4G4p10JHt16wuTJR5xyQnVd5YMp2ztZc+hNJ1AR/3BA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:52.246060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10619","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e003533ad90c05d3a47245916f70af5142ccddf8db050313e454d462890f7167","sha256:9762d10455218e8a72623c9d1dbd63241869d9e4ac5851614d6e0c7562d4c558"],"state_sha256":"c7b4645dde2b0a00189570566375e8a5564e53a02dc8f4269ae1174046638ff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gkODn6M720OKOyZGfvMdd6p123WQfJOOgvIrHM2oBsC5rATl01A9FpoboyZJ3n3GrZxXEI1zeHl8OOOdLsHKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T12:44:50.023520Z","bundle_sha256":"96d85c2de21b6680088d737989d8c8590e8dc2426c81866bd2875f1efc3996d9"}}