{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F25O6XWAICY77LXSRN4IIPVHC4","short_pith_number":"pith:F25O6XWA","schema_version":"1.0","canonical_sha256":"2ebaef5ec040b1ffaef28b78843ea717145787a0eb9e05138bbb213fea8540ad","source":{"kind":"arxiv","id":"2608.06930","version":1},"attestation_state":"computed","paper":{"title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohao Li, Kaituo Feng, Kaixiong Gong, Mingyang Wu, Xiangyu Yue, Zihao Yin","submitted_at":"2026-08-07T08:03:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.06930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T08:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"7f7f55ca7c47149abf55180d3bae93db9e78c13dd026e25aab4189bde742b897","abstract_canon_sha256":"73b7022b3921243ac34ab9195f198a3b6a9bd67c23fd856263c7fb1de2745aa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:32.842874Z","signature_b64":"/1hOnkJy89aGyBH1IteoRKqbf/2RVQ4yMQLLPfmQtfF2d2t20l1eQhHjjYzVCSWMn+JVI5JtOjJGULR2O2h0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ebaef5ec040b1ffaef28b78843ea717145787a0eb9e05138bbb213fea8540ad","last_reissued_at":"2026-08-10T01:12:32.840265Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:32.840265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohao Li, Kaituo Feng, Kaixiong Gong, Mingyang Wu, Xiangyu Yue, Zihao Yin","submitted_at":"2026-08-07T08:03:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06930","kind":"arxiv","version":1},"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/2608.06930/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.06930","created_at":"2026-08-10T01:12:32.841397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06930v1","created_at":"2026-08-10T01:12:32.841397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06930","created_at":"2026-08-10T01:12:32.841397+00:00"},{"alias_kind":"pith_short_12","alias_value":"F25O6XWAICY7","created_at":"2026-08-10T01:12:32.841397+00:00"},{"alias_kind":"pith_short_16","alias_value":"F25O6XWAICY77LXS","created_at":"2026-08-10T01:12:32.841397+00:00"},{"alias_kind":"pith_short_8","alias_value":"F25O6XWA","created_at":"2026-08-10T01:12:32.841397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4","json":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4.json","graph_json":"https://pith.science/api/pith-number/F25O6XWAICY77LXSRN4IIPVHC4/graph.json","events_json":"https://pith.science/api/pith-number/F25O6XWAICY77LXSRN4IIPVHC4/events.json","paper":"https://pith.science/paper/F25O6XWA"},"agent_actions":{"view_html":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4","download_json":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4.json","view_paper":"https://pith.science/paper/F25O6XWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06930&json=true","fetch_graph":"https://pith.science/api/pith-number/F25O6XWAICY77LXSRN4IIPVHC4/graph.json","fetch_events":"https://pith.science/api/pith-number/F25O6XWAICY77LXSRN4IIPVHC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4/action/storage_attestation","attest_author":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4/action/author_attestation","sign_citation":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4/action/citation_signature","submit_replication":"https://pith.science/pith/F25O6XWAICY77LXSRN4IIPVHC4/action/replication_record"}},"created_at":"2026-08-10T01:12:32.841397+00:00","updated_at":"2026-08-10T01:12:32.841397+00:00"}