{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WYNOXRROD7JSICPDE76436UYL7","short_pith_number":"pith:WYNOXRRO","schema_version":"1.0","canonical_sha256":"b61aebc62e1fd32409e327fdcdfa985fcdcfd6a14e2605c23be4b5b705b74228","source":{"kind":"arxiv","id":"2507.10053","version":1},"attestation_state":"computed","paper":{"title":"CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Artemis LLabr\\'es, Dimosthenis Karatzas, Emanuele Vivoli, Marc Serra Ortega","submitted_at":"2025-07-14T08:35:37Z","abstract_excerpt":"This paper introduces CoSMo, a novel multimodal Transformer for Page Stream Segmentation (PSS) in comic books, a critical task for automated content understanding, as it is a necessary first stage for many downstream tasks like character analysis, story indexing, or metadata enrichment. We formalize PSS for this unique medium and curate a new 20,800-page annotated dataset. CoSMo, developed in vision-only and multimodal variants, consistently outperforms traditional baselines and significantly larger general-purpose vision-language models across F1-Macro, Panoptic Quality, and stream-level metr"},"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":"2507.10053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T08:35:37Z","cross_cats_sorted":[],"title_canon_sha256":"ffb9f78df654781a02ed86320bfa9ec20022f82e9700e95b2d487c9550ec4c46","abstract_canon_sha256":"448809abdb4e97faa6df14dd6c0575ea0e4064fbf3c91dd16f493269cdb92305"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:44.291733Z","signature_b64":"RKflg+AXfoWaBJ88Bq3ZhA6HtJCmJnsF+4rLfEL9SU1/P8Id/LEXrBxv7n/BHY2heOe9t+Xl6X2znvtEs5KmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61aebc62e1fd32409e327fdcdfa985fcdcfd6a14e2605c23be4b5b705b74228","last_reissued_at":"2026-07-05T11:36:44.291158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:44.291158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Artemis LLabr\\'es, Dimosthenis Karatzas, Emanuele Vivoli, Marc Serra Ortega","submitted_at":"2025-07-14T08:35:37Z","abstract_excerpt":"This paper introduces CoSMo, a novel multimodal Transformer for Page Stream Segmentation (PSS) in comic books, a critical task for automated content understanding, as it is a necessary first stage for many downstream tasks like character analysis, story indexing, or metadata enrichment. We formalize PSS for this unique medium and curate a new 20,800-page annotated dataset. CoSMo, developed in vision-only and multimodal variants, consistently outperforms traditional baselines and significantly larger general-purpose vision-language models across F1-Macro, Panoptic Quality, and stream-level metr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10053","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/2507.10053/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":"2507.10053","created_at":"2026-07-05T11:36:44.291223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10053v1","created_at":"2026-07-05T11:36:44.291223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10053","created_at":"2026-07-05T11:36:44.291223+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYNOXRROD7JS","created_at":"2026-07-05T11:36:44.291223+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYNOXRROD7JSICPD","created_at":"2026-07-05T11:36:44.291223+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYNOXRRO","created_at":"2026-07-05T11:36:44.291223+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/WYNOXRROD7JSICPDE76436UYL7","json":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7.json","graph_json":"https://pith.science/api/pith-number/WYNOXRROD7JSICPDE76436UYL7/graph.json","events_json":"https://pith.science/api/pith-number/WYNOXRROD7JSICPDE76436UYL7/events.json","paper":"https://pith.science/paper/WYNOXRRO"},"agent_actions":{"view_html":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7","download_json":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7.json","view_paper":"https://pith.science/paper/WYNOXRRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10053&json=true","fetch_graph":"https://pith.science/api/pith-number/WYNOXRROD7JSICPDE76436UYL7/graph.json","fetch_events":"https://pith.science/api/pith-number/WYNOXRROD7JSICPDE76436UYL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7/action/storage_attestation","attest_author":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7/action/author_attestation","sign_citation":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7/action/citation_signature","submit_replication":"https://pith.science/pith/WYNOXRROD7JSICPDE76436UYL7/action/replication_record"}},"created_at":"2026-07-05T11:36:44.291223+00:00","updated_at":"2026-07-05T11:36:44.291223+00:00"}