{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6SDP3FBD5GEOFMNSWM2ABJ4T2W","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":"1627892750462eedd457e55f81f085c9531e4dc2cd6d065bb03d8bcdce7751db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T23:10:54Z","title_canon_sha256":"0e1b8d7b1eb1603d7197a2e405348e3abf15a63295190f091d02367933531cdf"},"schema_version":"1.0","source":{"id":"2412.09754","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09754","created_at":"2026-07-05T10:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09754v3","created_at":"2026-07-05T10:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09754","created_at":"2026-07-05T10:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"6SDP3FBD5GEO","created_at":"2026-07-05T10:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"6SDP3FBD5GEOFMNS","created_at":"2026-07-05T10:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"6SDP3FBD","created_at":"2026-07-05T10:43:41Z"}],"graph_snapshots":[{"event_id":"sha256:4b2231060048a45917082d721bf06b3967296a8f0185a32cbbb2d60a06e8f5d5","target":"graph","created_at":"2026-07-05T10:43:41Z","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/2412.09754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Ali Athar, Liang-Chieh Chen, Xueqing Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09754","kind":"arxiv","version":3},"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:f99aa110b536d59a54313f760386a1dce656192e29dd61e15482d456a0b6c324","target":"record","created_at":"2026-07-05T10:43:41Z","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":"1627892750462eedd457e55f81f085c9531e4dc2cd6d065bb03d8bcdce7751db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T23:10:54Z","title_canon_sha256":"0e1b8d7b1eb1603d7197a2e405348e3abf15a63295190f091d02367933531cdf"},"schema_version":"1.0","source":{"id":"2412.09754","kind":"arxiv","version":3}},"canonical_sha256":"f486fd9423e988e2b1b2b33400a793d5954244a50a8ff2c154cbc758dff82c5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f486fd9423e988e2b1b2b33400a793d5954244a50a8ff2c154cbc758dff82c5b","first_computed_at":"2026-07-05T10:43:41.913937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:41.913937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IiJI4inZ3vG9ZmacBK4VU8s0Zzof46MNGSF+K6F7yuHBRNnxocUzclropu4e+wqsvbCIoLt7IBbzHPS4NpcvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:41.914420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09754","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f99aa110b536d59a54313f760386a1dce656192e29dd61e15482d456a0b6c324","sha256:4b2231060048a45917082d721bf06b3967296a8f0185a32cbbb2d60a06e8f5d5"],"state_sha256":"f16cf6e5bac1b6ddcd4798018e4079ab3a2a6d9d34291473d7a5e62d88d31d42"}