{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E7WJYSSOK4Q4ZBKCC7ODFRQCBV","short_pith_number":"pith:E7WJYSSO","canonical_record":{"source":{"id":"2505.16493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"5ef61cb3a524cab7cefda95f2b4040814a4c83b6be4fa0881a6b47dbbfb7230d","abstract_canon_sha256":"eb0393d65080785318e23e09938a925a2dd33dabb8fa8ad263bf6b6916956ee4"},"schema_version":"1.0"},"canonical_sha256":"27ec9c4a4e5721cc854217dc32c6020d7704c18d3b4122ea63a5973b7c051062","source":{"kind":"arxiv","id":"2505.16493","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16493","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16493v1","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16493","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"E7WJYSSOK4Q4","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"E7WJYSSOK4Q4ZBKC","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"E7WJYSSO","created_at":"2026-07-05T11:07:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E7WJYSSOK4Q4ZBKCC7ODFRQCBV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"5ef61cb3a524cab7cefda95f2b4040814a4c83b6be4fa0881a6b47dbbfb7230d","abstract_canon_sha256":"eb0393d65080785318e23e09938a925a2dd33dabb8fa8ad263bf6b6916956ee4"},"schema_version":"1.0"},"canonical_sha256":"27ec9c4a4e5721cc854217dc32c6020d7704c18d3b4122ea63a5973b7c051062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:36.450423Z","signature_b64":"X11ldxv0y+oZBYJaBB1C64Atny0xS1Xrj+rUTSOyxDIP7E9jcdmhp1Lh6WAVfOakCXyp+Xr7CwrH0dxTM6E0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27ec9c4a4e5721cc854217dc32c6020d7704c18d3b4122ea63a5973b7c051062","last_reissued_at":"2026-07-05T11:07:36.449901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:36.449901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16493","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":"2026-07-05T11:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7+VHJijkC/DQ5MGkohbr09rivOz8APYNuIIAtkVp/G6/iUzt+H/zqat/064HvkjJxNmDH4ILbbn3fns9HbZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:59:50.518958Z"},"content_sha256":"7f561075e18bea60777f8b0324fc3cabaab20cf8c8e7752e3786d8f11ff5af03","schema_version":"1.0","event_id":"sha256:7f561075e18bea60777f8b0324fc3cabaab20cf8c8e7752e3786d8f11ff5af03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E7WJYSSOK4Q4ZBKCC7ODFRQCBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority Topics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaakko Peltonen, Seyedeh Fatemeh Ebrahimi","submitted_at":"2025-05-22T10:25:55Z","abstract_excerpt":"Topic models often fail to capture low-prevalence, domain-critical themes, so-called minority topics, such as mental health themes in online comments. While some existing methods can incorporate domain knowledge, such as expected topical content, methods allowing guidance may require overly detailed expected topics, hindering the discovery of topic divisions and variation. We propose a topic modeling solution via a specially constrained NMF. We incorporate a seed word list characterizing minority content of interest, but we do not require experts to pre-specify their division across minority t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16493","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/2505.16493/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":"2026-07-05T11:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1a1Oqoyv3gVcfwuLY386heGhDF8tFQJqwYUHBiHelcqu3pg8kcj5cFC6npdC3NWZDnpK51Pgw4pg530FL8C5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:59:50.519459Z"},"content_sha256":"75978350f3ee360ce0028bc321dcde9a15968e79eab3da65b7f03f3a170c6871","schema_version":"1.0","event_id":"sha256:75978350f3ee360ce0028bc321dcde9a15968e79eab3da65b7f03f3a170c6871"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/bundle.json","state_url":"https://pith.science/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/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":"2026-08-08T13:59:50Z","links":{"resolver":"https://pith.science/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV","bundle":"https://pith.science/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/bundle.json","state":"https://pith.science/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7WJYSSOK4Q4ZBKCC7ODFRQCBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E7WJYSSOK4Q4ZBKCC7ODFRQCBV","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":"eb0393d65080785318e23e09938a925a2dd33dabb8fa8ad263bf6b6916956ee4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:25:55Z","title_canon_sha256":"5ef61cb3a524cab7cefda95f2b4040814a4c83b6be4fa0881a6b47dbbfb7230d"},"schema_version":"1.0","source":{"id":"2505.16493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16493","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16493v1","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16493","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"E7WJYSSOK4Q4","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"E7WJYSSOK4Q4ZBKC","created_at":"2026-07-05T11:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"E7WJYSSO","created_at":"2026-07-05T11:07:36Z"}],"graph_snapshots":[{"event_id":"sha256:75978350f3ee360ce0028bc321dcde9a15968e79eab3da65b7f03f3a170c6871","target":"graph","created_at":"2026-07-05T11:07:36Z","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/2505.16493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models often fail to capture low-prevalence, domain-critical themes, so-called minority topics, such as mental health themes in online comments. While some existing methods can incorporate domain knowledge, such as expected topical content, methods allowing guidance may require overly detailed expected topics, hindering the discovery of topic divisions and variation. We propose a topic modeling solution via a specially constrained NMF. We incorporate a seed word list characterizing minority content of interest, but we do not require experts to pre-specify their division across minority t","authors_text":"Jaakko Peltonen, Seyedeh Fatemeh Ebrahimi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:25:55Z","title":"Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority Topics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16493","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":"sha256:7f561075e18bea60777f8b0324fc3cabaab20cf8c8e7752e3786d8f11ff5af03","target":"record","created_at":"2026-07-05T11:07:36Z","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":"eb0393d65080785318e23e09938a925a2dd33dabb8fa8ad263bf6b6916956ee4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T10:25:55Z","title_canon_sha256":"5ef61cb3a524cab7cefda95f2b4040814a4c83b6be4fa0881a6b47dbbfb7230d"},"schema_version":"1.0","source":{"id":"2505.16493","kind":"arxiv","version":1}},"canonical_sha256":"27ec9c4a4e5721cc854217dc32c6020d7704c18d3b4122ea63a5973b7c051062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27ec9c4a4e5721cc854217dc32c6020d7704c18d3b4122ea63a5973b7c051062","first_computed_at":"2026-07-05T11:07:36.449901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:36.449901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X11ldxv0y+oZBYJaBB1C64Atny0xS1Xrj+rUTSOyxDIP7E9jcdmhp1Lh6WAVfOakCXyp+Xr7CwrH0dxTM6E0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:36.450423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f561075e18bea60777f8b0324fc3cabaab20cf8c8e7752e3786d8f11ff5af03","sha256:75978350f3ee360ce0028bc321dcde9a15968e79eab3da65b7f03f3a170c6871"],"state_sha256":"c8b991ebdfe6eb216f83ccbde72f252060caeb4b5802cd8c336023cc52b2aaa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iNt6ikIRcg8lsCkvn/aB33HIiDebW63HGd4JVQyiTNZLX1+7HuIDQj9Wawsh+K5KNPXFWCQTSxkiO0iPPTtqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:59:50.524063Z","bundle_sha256":"24ab89453a74fc110b85d6235d7bb54dbacd5798e67937a65e72259121ffa802"}}