{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NSNGMJZR6TOOQW6XRH7QDRKJKK","short_pith_number":"pith:NSNGMJZR","canonical_record":{"source":{"id":"2508.18634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T03:18:34Z","cross_cats_sorted":[],"title_canon_sha256":"ccfbf4397f2e676fc688a1436879849d2acdda31197d0727a2ed31ef40bdc53b","abstract_canon_sha256":"8f28514dac5097d900a8b56fcf34a7ae29c7105b5c1241d52335741962276dab"},"schema_version":"1.0"},"canonical_sha256":"6c9a662731f4dce85bd789ff01c54952bdb706291fab893e694b4e9d155e25e6","source":{"kind":"arxiv","id":"2508.18634","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NSNGMJZR6TOOQW6XRH7QDRKJKK","target":"record","payload":{"canonical_record":{"source":{"id":"2508.18634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T03:18:34Z","cross_cats_sorted":[],"title_canon_sha256":"ccfbf4397f2e676fc688a1436879849d2acdda31197d0727a2ed31ef40bdc53b","abstract_canon_sha256":"8f28514dac5097d900a8b56fcf34a7ae29c7105b5c1241d52335741962276dab"},"schema_version":"1.0"},"canonical_sha256":"6c9a662731f4dce85bd789ff01c54952bdb706291fab893e694b4e9d155e25e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:10.324858Z","signature_b64":"Eml3kRONaZEdXax8MnrX+NvMJQoJOMsDXUvJgNNNxWJdKI4+nFcD03AOYv8P+u+dopq99+XUqKIL9gPG4LLrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c9a662731f4dce85bd789ff01c54952bdb706291fab893e694b4e9d155e25e6","last_reissued_at":"2026-07-05T12:00:10.324348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:10.324348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.18634","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFLNeKzL9tAPLcnCHPhABJxUSn1pMWqs7ntsdkFEZ4KV/NoybYyxiXskNwjaY0qQPRunYIyq5wZ3ziSh/Y6IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:04:46.643629Z"},"content_sha256":"c33b75f2fc7c2649067e7455303b5717de5200e7ddf23523cdbb6a45bd321b3e","schema_version":"1.0","event_id":"sha256:c33b75f2fc7c2649067e7455303b5717de5200e7ddf23523cdbb6a45bd321b3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NSNGMJZR6TOOQW6XRH7QDRKJKK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunlin Zhong, Haonan Lu, He Tang, Qiuxia Hou, Shuang Hao, Xiang Bai, Yanhao Zhang, Zhangjun Zhou","submitted_at":"2025-08-26T03:18:34Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18634","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/2508.18634/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtE/1K/KRpnWahmlrJ7U7hzqU/qZl5/8ZiKkMznVuyZj1jGPelrnP95o3kGf3V9xXNJk1EnPuodorYF6UV9PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:04:46.644006Z"},"content_sha256":"7314ac3fbd34bdeb694b48650fe6440b4a117a7e5c265feab71496373a5eacd7","schema_version":"1.0","event_id":"sha256:7314ac3fbd34bdeb694b48650fe6440b4a117a7e5c265feab71496373a5eacd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/bundle.json","state_url":"https://pith.science/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T04:04:46Z","links":{"resolver":"https://pith.science/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK","bundle":"https://pith.science/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/bundle.json","state":"https://pith.science/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NSNGMJZR6TOOQW6XRH7QDRKJKK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O8N8/ZfVljWr4FTiVQUpdvWrfHTmHG2SYZn0LdOC/vsrX0DgmTEqnMAEotFUbbwb+i1fMd1rwl08PAVL4k1YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:04:46.646670Z","bundle_sha256":"60e457d6e84e1070a57eab1d92ca89d4e627e7f77a7c55c82f0c6d35050972a8"}}