{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6SDP3FBD5GEOFMNSWM2ABJ4T2W","short_pith_number":"pith:6SDP3FBD","schema_version":"1.0","canonical_sha256":"f486fd9423e988e2b1b2b33400a793d5954244a50a8ff2c154cbc758dff82c5b","source":{"kind":"arxiv","id":"2412.09754","version":3},"attestation_state":"computed","paper":{"title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Athar, Liang-Chieh Chen, Xueqing Deng","submitted_at":"2024-12-12T23:10:54Z","abstract_excerpt":"Recent advances in multimodal large language models (MLLMs) have expanded research in video understanding, primarily focusing on high-level tasks such as video captioning and question-answering. Meanwhile, a smaller body of work addresses dense, pixel-precise segmentation tasks, which typically involve category-guided or referral-based object segmentation. Although both directions are essential for developing models with human-level video comprehension, they have largely evolved separately, with distinct benchmarks and architectures. This paper aims to unify these efforts by introducing ViCaS,"},"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":"2412.09754","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T23:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"0e1b8d7b1eb1603d7197a2e405348e3abf15a63295190f091d02367933531cdf","abstract_canon_sha256":"1627892750462eedd457e55f81f085c9531e4dc2cd6d065bb03d8bcdce7751db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:41.914420Z","signature_b64":"IiJI4inZ3vG9ZmacBK4VU8s0Zzof46MNGSF+K6F7yuHBRNnxocUzclropu4e+wqsvbCIoLt7IBbzHPS4NpcvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f486fd9423e988e2b1b2b33400a793d5954244a50a8ff2c154cbc758dff82c5b","last_reissued_at":"2026-07-05T10:43:41.913937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:41.913937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Athar, Liang-Chieh Chen, Xueqing Deng","submitted_at":"2024-12-12T23:10:54Z","abstract_excerpt":"Recent advances in multimodal large language models (MLLMs) have expanded research in video understanding, primarily focusing on high-level tasks such as video captioning and question-answering. Meanwhile, a smaller body of work addresses dense, pixel-precise segmentation tasks, which typically involve category-guided or referral-based object segmentation. Although both directions are essential for developing models with human-level video comprehension, they have largely evolved separately, with distinct benchmarks and architectures. This paper aims to unify these efforts by introducing ViCaS,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09754","kind":"arxiv","version":3},"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/2412.09754/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":"2412.09754","created_at":"2026-07-05T10:43:41.913996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09754v3","created_at":"2026-07-05T10:43:41.913996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09754","created_at":"2026-07-05T10:43:41.913996+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SDP3FBD5GEO","created_at":"2026-07-05T10:43:41.913996+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SDP3FBD5GEOFMNS","created_at":"2026-07-05T10:43:41.913996+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SDP3FBD","created_at":"2026-07-05T10:43:41.913996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04549","citing_title":"MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W","json":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W.json","graph_json":"https://pith.science/api/pith-number/6SDP3FBD5GEOFMNSWM2ABJ4T2W/graph.json","events_json":"https://pith.science/api/pith-number/6SDP3FBD5GEOFMNSWM2ABJ4T2W/events.json","paper":"https://pith.science/paper/6SDP3FBD"},"agent_actions":{"view_html":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W","download_json":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W.json","view_paper":"https://pith.science/paper/6SDP3FBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09754&json=true","fetch_graph":"https://pith.science/api/pith-number/6SDP3FBD5GEOFMNSWM2ABJ4T2W/graph.json","fetch_events":"https://pith.science/api/pith-number/6SDP3FBD5GEOFMNSWM2ABJ4T2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W/action/storage_attestation","attest_author":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W/action/author_attestation","sign_citation":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W/action/citation_signature","submit_replication":"https://pith.science/pith/6SDP3FBD5GEOFMNSWM2ABJ4T2W/action/replication_record"}},"created_at":"2026-07-05T10:43:41.913996+00:00","updated_at":"2026-07-05T10:43:41.913996+00:00"}