{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RYVG7OPS6GAOYJF4R2IZRJQKU2","short_pith_number":"pith:RYVG7OPS","schema_version":"1.0","canonical_sha256":"8e2a6fb9f2f180ec24bc8e9198a60aa6838b296638a145f49ac075dd68cfb41c","source":{"kind":"arxiv","id":"2506.16716","version":1},"attestation_state":"computed","paper":{"title":"V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chenglin Guo, Qixin Wang, Shikun Sun, Songtao Zhou, Xiaoyu Qin, Zeyu Jin","submitted_at":"2025-06-20T03:24:34Z","abstract_excerpt":"Automatic video commentary systems are widely used on multimedia social media platforms to extract factual information about video content. However, current systems may overlook essential para-linguistic cues, including emotion and attitude, which are critical for fully conveying the meaning of visual content. The absence of these cues can limit user understanding or, in some cases, distort the video's original intent. Expressive speech effectively conveys these cues and enhances the user's comprehension of videos. Building on these insights, this paper explores the usage of vision-context-awa"},"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":"2506.16716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-06-20T03:24:34Z","cross_cats_sorted":[],"title_canon_sha256":"4ab7425eec819fa7b9af6b9a67321c28f476199fcd57b8e172de4c342dbcb935","abstract_canon_sha256":"f8423a56a4a7c1ed56f4ccd808a1c4991f2c55accf7870e67e28320eea172b25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:41.533268Z","signature_b64":"LhlBgwjac7tHjAzpBc2DquYd7Hk89Tid414IurYU4W1BDNeJHgnLcyVBJ1TvrDWn3XiZV0S+x4RuGvFI8rdwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2a6fb9f2f180ec24bc8e9198a60aa6838b296638a145f49ac075dd68cfb41c","last_reissued_at":"2026-07-05T11:24:41.532804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:41.532804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chenglin Guo, Qixin Wang, Shikun Sun, Songtao Zhou, Xiaoyu Qin, Zeyu Jin","submitted_at":"2025-06-20T03:24:34Z","abstract_excerpt":"Automatic video commentary systems are widely used on multimedia social media platforms to extract factual information about video content. However, current systems may overlook essential para-linguistic cues, including emotion and attitude, which are critical for fully conveying the meaning of visual content. The absence of these cues can limit user understanding or, in some cases, distort the video's original intent. Expressive speech effectively conveys these cues and enhances the user's comprehension of videos. Building on these insights, this paper explores the usage of vision-context-awa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16716","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/2506.16716/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":"2506.16716","created_at":"2026-07-05T11:24:41.532859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16716v1","created_at":"2026-07-05T11:24:41.532859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16716","created_at":"2026-07-05T11:24:41.532859+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYVG7OPS6GAO","created_at":"2026-07-05T11:24:41.532859+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYVG7OPS6GAOYJF4","created_at":"2026-07-05T11:24:41.532859+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYVG7OPS","created_at":"2026-07-05T11:24:41.532859+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/RYVG7OPS6GAOYJF4R2IZRJQKU2","json":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2.json","graph_json":"https://pith.science/api/pith-number/RYVG7OPS6GAOYJF4R2IZRJQKU2/graph.json","events_json":"https://pith.science/api/pith-number/RYVG7OPS6GAOYJF4R2IZRJQKU2/events.json","paper":"https://pith.science/paper/RYVG7OPS"},"agent_actions":{"view_html":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2","download_json":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2.json","view_paper":"https://pith.science/paper/RYVG7OPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16716&json=true","fetch_graph":"https://pith.science/api/pith-number/RYVG7OPS6GAOYJF4R2IZRJQKU2/graph.json","fetch_events":"https://pith.science/api/pith-number/RYVG7OPS6GAOYJF4R2IZRJQKU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2/action/storage_attestation","attest_author":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2/action/author_attestation","sign_citation":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2/action/citation_signature","submit_replication":"https://pith.science/pith/RYVG7OPS6GAOYJF4R2IZRJQKU2/action/replication_record"}},"created_at":"2026-07-05T11:24:41.532859+00:00","updated_at":"2026-07-05T11:24:41.532859+00:00"}