{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HD27CLZ6DNOFXBUB75GH5NS7EW","short_pith_number":"pith:HD27CLZ6","schema_version":"1.0","canonical_sha256":"38f5f12f3e1b5c5b8681ff4c7eb65f25a48270862f5407099c154202482ca8c5","source":{"kind":"arxiv","id":"2104.02656","version":1},"attestation_state":"computed","paper":{"title":"Collaborative Learning to Generate Audio-Video Jointly","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Badri N Patro, K S Venkatesh, Preethi Jyothi, Vinay P Namboodiri, Vinod K Kurmi, Vipul Bajaj","submitted_at":"2021-04-01T01:00:51Z","abstract_excerpt":"There have been a number of techniques that have demonstrated the generation of multimedia data for one modality at a time using GANs, such as the ability to generate images, videos, and audio. However, so far, the task of multi-modal generation of data, specifically for audio and videos both, has not been sufficiently well-explored. Towards this, we propose a method that demonstrates that we are able to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities. The proposed method uses multiple discriminators to ensure that the audi"},"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":"2104.02656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T01:00:51Z","cross_cats_sorted":["cs.AI","cs.GR","cs.MM","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"d0e664c64102bd2cc4ba828df687ae8c178ecce1327492cee7e40839ab34ab5f","abstract_canon_sha256":"49dfd51ed4b5a781b220ac0dc5b989eb8319daf18c0aa1dcce650ad9220b274f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:50.668786Z","signature_b64":"KCKFdwmLWxkcGu8k50JZYmFxhN5GcaztEdoTVLNGBFfT703iRTHeVZ+fYNWVR4uJ0VN3/HBxtsMJsmoWJaeNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f5f12f3e1b5c5b8681ff4c7eb65f25a48270862f5407099c154202482ca8c5","last_reissued_at":"2026-07-05T02:29:50.668279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:50.668279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Learning to Generate Audio-Video Jointly","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.MM","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Badri N Patro, K S Venkatesh, Preethi Jyothi, Vinay P Namboodiri, Vinod K Kurmi, Vipul Bajaj","submitted_at":"2021-04-01T01:00:51Z","abstract_excerpt":"There have been a number of techniques that have demonstrated the generation of multimedia data for one modality at a time using GANs, such as the ability to generate images, videos, and audio. However, so far, the task of multi-modal generation of data, specifically for audio and videos both, has not been sufficiently well-explored. Towards this, we propose a method that demonstrates that we are able to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities. The proposed method uses multiple discriminators to ensure that the audi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02656","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/2104.02656/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":"2104.02656","created_at":"2026-07-05T02:29:50.668346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02656v1","created_at":"2026-07-05T02:29:50.668346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02656","created_at":"2026-07-05T02:29:50.668346+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD27CLZ6DNOF","created_at":"2026-07-05T02:29:50.668346+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD27CLZ6DNOFXBUB","created_at":"2026-07-05T02:29:50.668346+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD27CLZ6","created_at":"2026-07-05T02:29:50.668346+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/HD27CLZ6DNOFXBUB75GH5NS7EW","json":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW.json","graph_json":"https://pith.science/api/pith-number/HD27CLZ6DNOFXBUB75GH5NS7EW/graph.json","events_json":"https://pith.science/api/pith-number/HD27CLZ6DNOFXBUB75GH5NS7EW/events.json","paper":"https://pith.science/paper/HD27CLZ6"},"agent_actions":{"view_html":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW","download_json":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW.json","view_paper":"https://pith.science/paper/HD27CLZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02656&json=true","fetch_graph":"https://pith.science/api/pith-number/HD27CLZ6DNOFXBUB75GH5NS7EW/graph.json","fetch_events":"https://pith.science/api/pith-number/HD27CLZ6DNOFXBUB75GH5NS7EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW/action/storage_attestation","attest_author":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW/action/author_attestation","sign_citation":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW/action/citation_signature","submit_replication":"https://pith.science/pith/HD27CLZ6DNOFXBUB75GH5NS7EW/action/replication_record"}},"created_at":"2026-07-05T02:29:50.668346+00:00","updated_at":"2026-07-05T02:29:50.668346+00:00"}