{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B6R6DHLB3GEPBKLHMIPDIOOCD2","short_pith_number":"pith:B6R6DHLB","schema_version":"1.0","canonical_sha256":"0fa3e19d61d988f0a967621e3439c21e9c6cf67f8726e415bbb988e1fa83fb6b","source":{"kind":"arxiv","id":"2506.10416","version":2},"attestation_state":"computed","paper":{"title":"Can Sound Replace Vision in LLaVA With Token Substitution?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Ali Vosoughi, Chenliang Xu, Jing Bi, Pinxin Liu, Yunlong Tang","submitted_at":"2025-06-12T07:14:23Z","abstract_excerpt":"What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either synchronized or not. To address this limitation, we developed a comprehensive dataset featuring detailed alignment scores that reveal the hidden spectrum of audio-visual perceptual correspondence. Using these precise scores, we create \"superaligned\" representations by training exclusively on the most perfectly matched audio-visual pairs, then conduct our syste"},"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":"2506.10416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-12T07:14:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6ed3448d2722e73d84abe6c903cd6b46e614b7c56d241e5244602fefb7fd7d90","abstract_canon_sha256":"e9d7c80f0ecd2af11abb495b29096f93cc596be337d6bc5f4cd31d7fb873b63d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:10.761626Z","signature_b64":"XKV9+jb2dCTxxrSHHvJSDDX8Vq3yFgiRu+UwrerGM1J9lu5Aviz/vacxCBA1k1GWGxm4/jwwPbwkN9z4RG+dDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa3e19d61d988f0a967621e3439c21e9c6cf67f8726e415bbb988e1fa83fb6b","last_reissued_at":"2026-07-05T11:49:10.761135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:10.761135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Sound Replace Vision in LLaVA With Token Substitution?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Ali Vosoughi, Chenliang Xu, Jing Bi, Pinxin Liu, Yunlong Tang","submitted_at":"2025-06-12T07:14:23Z","abstract_excerpt":"What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either synchronized or not. To address this limitation, we developed a comprehensive dataset featuring detailed alignment scores that reveal the hidden spectrum of audio-visual perceptual correspondence. Using these precise scores, we create \"superaligned\" representations by training exclusively on the most perfectly matched audio-visual pairs, then conduct our syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10416","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/2506.10416/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":"2506.10416","created_at":"2026-07-05T11:49:10.761192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10416v2","created_at":"2026-07-05T11:49:10.761192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10416","created_at":"2026-07-05T11:49:10.761192+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6R6DHLB3GEP","created_at":"2026-07-05T11:49:10.761192+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6R6DHLB3GEPBKLH","created_at":"2026-07-05T11:49:10.761192+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6R6DHLB","created_at":"2026-07-05T11:49:10.761192+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/B6R6DHLB3GEPBKLHMIPDIOOCD2","json":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2.json","graph_json":"https://pith.science/api/pith-number/B6R6DHLB3GEPBKLHMIPDIOOCD2/graph.json","events_json":"https://pith.science/api/pith-number/B6R6DHLB3GEPBKLHMIPDIOOCD2/events.json","paper":"https://pith.science/paper/B6R6DHLB"},"agent_actions":{"view_html":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2","download_json":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2.json","view_paper":"https://pith.science/paper/B6R6DHLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10416&json=true","fetch_graph":"https://pith.science/api/pith-number/B6R6DHLB3GEPBKLHMIPDIOOCD2/graph.json","fetch_events":"https://pith.science/api/pith-number/B6R6DHLB3GEPBKLHMIPDIOOCD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2/action/storage_attestation","attest_author":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2/action/author_attestation","sign_citation":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2/action/citation_signature","submit_replication":"https://pith.science/pith/B6R6DHLB3GEPBKLHMIPDIOOCD2/action/replication_record"}},"created_at":"2026-07-05T11:49:10.761192+00:00","updated_at":"2026-07-05T11:49:10.761192+00:00"}