{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NBY5ZAELWX5LEDIDET2J2WX2JH","short_pith_number":"pith:NBY5ZAEL","schema_version":"1.0","canonical_sha256":"6871dc808bb5fab20d0324f49d5afa49ffa042526352b1a1b4d69ace0538dc13","source":{"kind":"arxiv","id":"2606.26845","version":1},"attestation_state":"computed","paper":{"title":"A Shared IPTC Topic Space for Cross-Source Topic Modelling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aline Villavicencio, Din Iskakov, Marco Idiat, Mendeli Vainstein, Rodrigo Wilkens, Ronaldo Menezes, Sebastian Gon\\c{c}alves","submitted_at":"2026-06-25T10:32:41Z","abstract_excerpt":"Comparing topic attention across different media is hindered by a fundamental modelling problem: topic models fitted separately to each corpus produce corpus-specific topic spaces that cannot be aligned directly. This paper presents a reproducible framework that places corpora in a single shared topic space defined by a taxonomy. Discovered topics are obtained with guided BERTopic, scored against the ninety-four IPTC Media Topics' taxonomy topics (level-1) through weighted keyword and target centroids, and then collapsed upward to seventeen IPTC parent topics by a maximum-similarity rule. The "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.26845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-25T10:32:41Z","cross_cats_sorted":[],"title_canon_sha256":"5eacdab5baba877411d0ecdd1d1cb05a3918cf8853dbef660c39c0c7f34fc1d2","abstract_canon_sha256":"96eb30da086acc5dcfc82ca13d93d80e21f00394d5ca1ccb4a75e7a10c6d7511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:01.490178Z","signature_b64":"sKwAoU9uzLXEAc+1lN7+MZKuzIzU8GWoORzMV7riZx7TplJBfSGJ4QzrMI+RRSo/9fClkqCHefg1gXZpqwjxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6871dc808bb5fab20d0324f49d5afa49ffa042526352b1a1b4d69ace0538dc13","last_reissued_at":"2026-06-26T01:16:01.489632Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:01.489632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Shared IPTC Topic Space for Cross-Source Topic Modelling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aline Villavicencio, Din Iskakov, Marco Idiat, Mendeli Vainstein, Rodrigo Wilkens, Ronaldo Menezes, Sebastian Gon\\c{c}alves","submitted_at":"2026-06-25T10:32:41Z","abstract_excerpt":"Comparing topic attention across different media is hindered by a fundamental modelling problem: topic models fitted separately to each corpus produce corpus-specific topic spaces that cannot be aligned directly. This paper presents a reproducible framework that places corpora in a single shared topic space defined by a taxonomy. Discovered topics are obtained with guided BERTopic, scored against the ninety-four IPTC Media Topics' taxonomy topics (level-1) through weighted keyword and target centroids, and then collapsed upward to seventeen IPTC parent topics by a maximum-similarity rule. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26845","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/2606.26845/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.26845","created_at":"2026-06-26T01:16:01.489743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26845v1","created_at":"2026-06-26T01:16:01.489743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26845","created_at":"2026-06-26T01:16:01.489743+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBY5ZAELWX5L","created_at":"2026-06-26T01:16:01.489743+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBY5ZAELWX5LEDID","created_at":"2026-06-26T01:16:01.489743+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBY5ZAEL","created_at":"2026-06-26T01:16:01.489743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH","json":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH.json","graph_json":"https://pith.science/api/pith-number/NBY5ZAELWX5LEDIDET2J2WX2JH/graph.json","events_json":"https://pith.science/api/pith-number/NBY5ZAELWX5LEDIDET2J2WX2JH/events.json","paper":"https://pith.science/paper/NBY5ZAEL"},"agent_actions":{"view_html":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH","download_json":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH.json","view_paper":"https://pith.science/paper/NBY5ZAEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26845&json=true","fetch_graph":"https://pith.science/api/pith-number/NBY5ZAELWX5LEDIDET2J2WX2JH/graph.json","fetch_events":"https://pith.science/api/pith-number/NBY5ZAELWX5LEDIDET2J2WX2JH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH/action/storage_attestation","attest_author":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH/action/author_attestation","sign_citation":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH/action/citation_signature","submit_replication":"https://pith.science/pith/NBY5ZAELWX5LEDIDET2J2WX2JH/action/replication_record"}},"created_at":"2026-06-26T01:16:01.489743+00:00","updated_at":"2026-06-26T01:16:01.489743+00:00"}