{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4BCVBRDNYPY4FHIBUWF6LWM76","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":"e4eb8eea15ae06c56b3574d09c53be6f3964c41fba2c1d73dc6b8224d0307f38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T10:08:26Z","title_canon_sha256":"7305636a5dc6b0326ea6897bc0246407169aecc7b1b959adea4a9a21e717860a"},"schema_version":"1.0","source":{"id":"2501.06761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06761","created_at":"2026-07-05T10:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06761v1","created_at":"2026-07-05T10:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06761","created_at":"2026-07-05T10:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"K4BCVBRDNYPY","created_at":"2026-07-05T10:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"K4BCVBRDNYPY4FHI","created_at":"2026-07-05T10:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"K4BCVBRD","created_at":"2026-07-05T10:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:b309401d82de14734b6899c9a0f4049fdd71f38665f89c4855ce5d41bfd75fdc","target":"graph","created_at":"2026-07-05T10:00:09Z","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/2501.06761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC). DVC is a complicated task of describing all events within a video while also temporally localizing them, which integrates multiple fine-grained tasks, including video segmentation, video captioning, and temporal video grounding. Previous VideoLLMs attempt to solve DVC in a single step, failing to utilize their reasoning capability. Moreover, previous training objectives for VideoLLMs do not fully reflect the evaluati","authors_text":"Hyunwoo J. Kim, Jeehye Na, Jinyoung Park, Ji Soo Lee, Jongha Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T10:08:26Z","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06761","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":"sha256:9544e6f2c30df6053bcf71b1e2ba5d86625b5a7338e5523b3b20d4e20fb119c3","target":"record","created_at":"2026-07-05T10:00:09Z","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":"e4eb8eea15ae06c56b3574d09c53be6f3964c41fba2c1d73dc6b8224d0307f38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T10:08:26Z","title_canon_sha256":"7305636a5dc6b0326ea6897bc0246407169aecc7b1b959adea4a9a21e717860a"},"schema_version":"1.0","source":{"id":"2501.06761","kind":"arxiv","version":1}},"canonical_sha256":"57022a86236e1f8e14e80d2c5f2eccffb625a606054136fc7aba58b9f7dad127","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57022a86236e1f8e14e80d2c5f2eccffb625a606054136fc7aba58b9f7dad127","first_computed_at":"2026-07-05T10:00:09.815285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:09.815285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WB3UsvF+bt8xaovI+HMLZFTnPLu1e9ctdovi18ThluTGx+VaZ4zcZCCxPGIkN8JHTmaydXjVDB7t9CIKJ4UgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:09.815786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9544e6f2c30df6053bcf71b1e2ba5d86625b5a7338e5523b3b20d4e20fb119c3","sha256:b309401d82de14734b6899c9a0f4049fdd71f38665f89c4855ce5d41bfd75fdc"],"state_sha256":"25398c45ce6756d1c7fa8ceaeeddfeb6c24a4ddca675864d23f79442267466c6"}