{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WYNOXRROD7JSICPDE76436UYL7","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":"448809abdb4e97faa6df14dd6c0575ea0e4064fbf3c91dd16f493269cdb92305","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T08:35:37Z","title_canon_sha256":"ffb9f78df654781a02ed86320bfa9ec20022f82e9700e95b2d487c9550ec4c46"},"schema_version":"1.0","source":{"id":"2507.10053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10053","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10053v1","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10053","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"WYNOXRROD7JS","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"WYNOXRROD7JSICPD","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"WYNOXRRO","created_at":"2026-07-05T11:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:81eb054aeee01057c768d675dad82a421298d6c41ab42373fcb8dbd85a678c01","target":"graph","created_at":"2026-07-05T11:36:44Z","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/2507.10053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Artemis LLabr\\'es, Dimosthenis Karatzas, Emanuele Vivoli, Marc Serra Ortega","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T08:35:37Z","title":"CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10053","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:d542bf31b45b2afbca1d257a94ae68dabd851f65e6db22eec6f83d6f89ba99b4","target":"record","created_at":"2026-07-05T11:36:44Z","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":"448809abdb4e97faa6df14dd6c0575ea0e4064fbf3c91dd16f493269cdb92305","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T08:35:37Z","title_canon_sha256":"ffb9f78df654781a02ed86320bfa9ec20022f82e9700e95b2d487c9550ec4c46"},"schema_version":"1.0","source":{"id":"2507.10053","kind":"arxiv","version":1}},"canonical_sha256":"b61aebc62e1fd32409e327fdcdfa985fcdcfd6a14e2605c23be4b5b705b74228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b61aebc62e1fd32409e327fdcdfa985fcdcfd6a14e2605c23be4b5b705b74228","first_computed_at":"2026-07-05T11:36:44.291158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:44.291158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKflg+AXfoWaBJ88Bq3ZhA6HtJCmJnsF+4rLfEL9SU1/P8Id/LEXrBxv7n/BHY2heOe9t+Xl6X2znvtEs5KmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:44.291733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d542bf31b45b2afbca1d257a94ae68dabd851f65e6db22eec6f83d6f89ba99b4","sha256:81eb054aeee01057c768d675dad82a421298d6c41ab42373fcb8dbd85a678c01"],"state_sha256":"ab2b7d3a4edf93349dbebfb80cd0f88595a449347f08487ba50b1e09b234f075"}