{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NSNGMJZR6TOOQW6XRH7QDRKJKK","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":"8f28514dac5097d900a8b56fcf34a7ae29c7105b5c1241d52335741962276dab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T03:18:34Z","title_canon_sha256":"ccfbf4397f2e676fc688a1436879849d2acdda31197d0727a2ed31ef40bdc53b"},"schema_version":"1.0","source":{"id":"2508.18634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18634","created_at":"2026-07-05T12:00:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18634v2","created_at":"2026-07-05T12:00:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18634","created_at":"2026-07-05T12:00:10Z"},{"alias_kind":"pith_short_12","alias_value":"NSNGMJZR6TOO","created_at":"2026-07-05T12:00:10Z"},{"alias_kind":"pith_short_16","alias_value":"NSNGMJZR6TOOQW6X","created_at":"2026-07-05T12:00:10Z"},{"alias_kind":"pith_short_8","alias_value":"NSNGMJZR","created_at":"2026-07-05T12:00:10Z"}],"graph_snapshots":[{"event_id":"sha256:7314ac3fbd34bdeb694b48650fe6440b4a117a7e5c265feab71496373a5eacd7","target":"graph","created_at":"2026-07-05T12:00:10Z","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/2508.18634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance, as models tend to overemphasize one aspect while neglecting the other. This imbalance results in incomplete captions, which in turn leads to a lack of consistency in video understanding and generation. To address this issue, we propose solutions from two aspects: 1) Data aspect: We constructed the Harmonizing Motion-Detail 270K (HMD-270K) dataset through a ","authors_text":"Chunlin Zhong, Haonan Lu, He Tang, Qiuxia Hou, Shuang Hao, Xiang Bai, Yanhao Zhang, Zhangjun Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T03:18:34Z","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18634","kind":"arxiv","version":2},"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:c33b75f2fc7c2649067e7455303b5717de5200e7ddf23523cdbb6a45bd321b3e","target":"record","created_at":"2026-07-05T12:00:10Z","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":"8f28514dac5097d900a8b56fcf34a7ae29c7105b5c1241d52335741962276dab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T03:18:34Z","title_canon_sha256":"ccfbf4397f2e676fc688a1436879849d2acdda31197d0727a2ed31ef40bdc53b"},"schema_version":"1.0","source":{"id":"2508.18634","kind":"arxiv","version":2}},"canonical_sha256":"6c9a662731f4dce85bd789ff01c54952bdb706291fab893e694b4e9d155e25e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c9a662731f4dce85bd789ff01c54952bdb706291fab893e694b4e9d155e25e6","first_computed_at":"2026-07-05T12:00:10.324348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:10.324348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eml3kRONaZEdXax8MnrX+NvMJQoJOMsDXUvJgNNNxWJdKI4+nFcD03AOYv8P+u+dopq99+XUqKIL9gPG4LLrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:10.324858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c33b75f2fc7c2649067e7455303b5717de5200e7ddf23523cdbb6a45bd321b3e","sha256:7314ac3fbd34bdeb694b48650fe6440b4a117a7e5c265feab71496373a5eacd7"],"state_sha256":"952e91608544b315c3e51f666f54ad4328da159f5c982285775ddd2b773979ca"}