{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHMY4SL6Q5T7KH4VUE3VSDK76C","short_pith_number":"pith:NHMY4SL6","schema_version":"1.0","canonical_sha256":"69d98e497e8767f51f95a137590d5ff09c53fdb6b5a4cee7f83c5735f6d0f504","source":{"kind":"arxiv","id":"2409.09502","version":2},"attestation_state":"computed","paper":{"title":"One missing piece in Vision and Language: A Survey on Comics Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrey Barsky, Artemis LLabr\\'es, Dimosthenis Karatzas, Emanuele Vivoli, Marco Bertini, Mohamed Ali Souibgui","submitted_at":"2024-09-14T18:26:26Z","abstract_excerpt":"Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics "},"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":"2409.09502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T18:26:26Z","cross_cats_sorted":[],"title_canon_sha256":"c292aaedaedf50c8428cb7c2ac8ca7d2bc39643b1893da81e4240230e3246890","abstract_canon_sha256":"5be4381e27702503b14a111c533a351adfac2356b40e8089a34716a12247bbbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:24.392094Z","signature_b64":"o1VrWJtBdthH9RR8mnBalIFLMzcBhmZ+5rxIWCZ30FIcsJfCmnEf3ooPQYJds9ukwbmgUhcodBwsVTaScVI6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d98e497e8767f51f95a137590d5ff09c53fdb6b5a4cee7f83c5735f6d0f504","last_reissued_at":"2026-07-05T09:58:24.391609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:24.391609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One missing piece in Vision and Language: A Survey on Comics Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrey Barsky, Artemis LLabr\\'es, Dimosthenis Karatzas, Emanuele Vivoli, Marco Bertini, Mohamed Ali Souibgui","submitted_at":"2024-09-14T18:26:26Z","abstract_excerpt":"Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09502","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/2409.09502/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":"2409.09502","created_at":"2026-07-05T09:58:24.391666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09502v2","created_at":"2026-07-05T09:58:24.391666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09502","created_at":"2026-07-05T09:58:24.391666+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHMY4SL6Q5T7","created_at":"2026-07-05T09:58:24.391666+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHMY4SL6Q5T7KH4V","created_at":"2026-07-05T09:58:24.391666+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHMY4SL6","created_at":"2026-07-05T09:58:24.391666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21182","citing_title":"Manga109-v2026: Revisiting Manga109 Annotations for Modern Manga Understanding","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C","json":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C.json","graph_json":"https://pith.science/api/pith-number/NHMY4SL6Q5T7KH4VUE3VSDK76C/graph.json","events_json":"https://pith.science/api/pith-number/NHMY4SL6Q5T7KH4VUE3VSDK76C/events.json","paper":"https://pith.science/paper/NHMY4SL6"},"agent_actions":{"view_html":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C","download_json":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C.json","view_paper":"https://pith.science/paper/NHMY4SL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09502&json=true","fetch_graph":"https://pith.science/api/pith-number/NHMY4SL6Q5T7KH4VUE3VSDK76C/graph.json","fetch_events":"https://pith.science/api/pith-number/NHMY4SL6Q5T7KH4VUE3VSDK76C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C/action/storage_attestation","attest_author":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C/action/author_attestation","sign_citation":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C/action/citation_signature","submit_replication":"https://pith.science/pith/NHMY4SL6Q5T7KH4VUE3VSDK76C/action/replication_record"}},"created_at":"2026-07-05T09:58:24.391666+00:00","updated_at":"2026-07-05T09:58:24.391666+00:00"}