{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F25O6XWAICY77LXSRN4IIPVHC4","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":"73b7022b3921243ac34ab9195f198a3b6a9bd67c23fd856263c7fb1de2745aa9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T08:03:51Z","title_canon_sha256":"7f7f55ca7c47149abf55180d3bae93db9e78c13dd026e25aab4189bde742b897"},"schema_version":"1.0","source":{"id":"2608.06930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06930","created_at":"2026-08-10T01:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06930v1","created_at":"2026-08-10T01:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06930","created_at":"2026-08-10T01:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"F25O6XWAICY7","created_at":"2026-08-10T01:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"F25O6XWAICY77LXS","created_at":"2026-08-10T01:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"F25O6XWA","created_at":"2026-08-10T01:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:e85e74353aefdab7f059d9c2d46ead406ed4fe578280ef0be0ff0c447ced0cc8","target":"graph","created_at":"2026-08-10T01:12:32Z","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/2608.06930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detailed audio-video joint captioning is essential for multimodal video understanding and generation. However, prior works are constrained by three main limitations: (1) the scarcity of high-quality public datasets with fine-grained audio-visual joint captions; (2) reinforcement-learning methods that rely on coarse reward signals; and (3) the lack of a benchmark and metric for evaluating detailed audiovisual captions at the atomic level. To address these challenges, we propose: (1) AVCap-100K, a high-quality dataset of 100K temporally aligned, detail-rich audio-video captions; (2) AVCap, a mod","authors_text":"Bohao Li, Kaituo Feng, Kaixiong Gong, Mingyang Wu, Xiangyu Yue, Zihao Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T08:03:51Z","title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06930","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:c77c087c2cdf29a53072e8283b15c1a613579bd57f47fb06192050714ae1b216","target":"record","created_at":"2026-08-10T01:12:32Z","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":"73b7022b3921243ac34ab9195f198a3b6a9bd67c23fd856263c7fb1de2745aa9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T08:03:51Z","title_canon_sha256":"7f7f55ca7c47149abf55180d3bae93db9e78c13dd026e25aab4189bde742b897"},"schema_version":"1.0","source":{"id":"2608.06930","kind":"arxiv","version":1}},"canonical_sha256":"2ebaef5ec040b1ffaef28b78843ea717145787a0eb9e05138bbb213fea8540ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ebaef5ec040b1ffaef28b78843ea717145787a0eb9e05138bbb213fea8540ad","first_computed_at":"2026-08-10T01:12:32.840265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:12:32.840265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/1hOnkJy89aGyBH1IteoRKqbf/2RVQ4yMQLLPfmQtfF2d2t20l1eQhHjjYzVCSWMn+JVI5JtOjJGULR2O2h0Bg==","signature_status":"signed_v1","signed_at":"2026-08-10T01:12:32.842874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c77c087c2cdf29a53072e8283b15c1a613579bd57f47fb06192050714ae1b216","sha256:e85e74353aefdab7f059d9c2d46ead406ed4fe578280ef0be0ff0c447ced0cc8"],"state_sha256":"104fafebdf0c8bd5bb098b5311c2d989860a8b98d1e59cc4314987eea1e4122b"}