{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7RKTK473JJSFLO7XS4YGUQKZBB","short_pith_number":"pith:7RKTK473","canonical_record":{"source":{"id":"2608.05798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:34:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"29a7eeee6efefcd7d2f5662d0b614f4c5226e2283f5fc2a999f7c6b32d59486a","abstract_canon_sha256":"6a166dd82ddf7c53fab640ee67186f1a8905db724891e0e8d6dcbcea01526d74"},"schema_version":"1.0"},"canonical_sha256":"fc553573fb4a6455bbf797306a41590864f8deadc9f0cca15761176437ea0049","source":{"kind":"arxiv","id":"2608.05798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05798","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05798v1","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05798","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"7RKTK473JJSF","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"7RKTK473JJSFLO7X","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"7RKTK473","created_at":"2026-08-07T00:52:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7RKTK473JJSFLO7XS4YGUQKZBB","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:34:00Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"29a7eeee6efefcd7d2f5662d0b614f4c5226e2283f5fc2a999f7c6b32d59486a","abstract_canon_sha256":"6a166dd82ddf7c53fab640ee67186f1a8905db724891e0e8d6dcbcea01526d74"},"schema_version":"1.0"},"canonical_sha256":"fc553573fb4a6455bbf797306a41590864f8deadc9f0cca15761176437ea0049","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:46.383599Z","signature_b64":"xVc2AaKePxAY95O4BH+0TafZUdnSff9hVRg42NTTBhNHbKooeQYADzMlwZozjITNd+TnnzlupWRHKsVgFmd/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc553573fb4a6455bbf797306a41590864f8deadc9f0cca15761176437ea0049","last_reissued_at":"2026-08-07T00:52:46.382099Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:46.382099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05798","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-07T00:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83WfO+VYTpv6U9UOTmVDcEyHPCb+MTgDPJQwgWfdxzxsD1zKhxLQKoV+xKT1dKODERVpSsJOSs0PBnL7eQPyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:42:42.359757Z"},"content_sha256":"df7e503805ed8339c63604e4d1cb2a6a341a715bfce7e3ee829c2d00dc61698c","schema_version":"1.0","event_id":"sha256:df7e503805ed8339c63604e4d1cb2a6a341a715bfce7e3ee829c2d00dc61698c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7RKTK473JJSFLO7XS4YGUQKZBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KVAE: Family of Tokenizers for Multimodal Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CV","authors_text":"Alexander Ivanov, Andrey Shutkin, Azat Saginbaev, David Chikovani, Denis Parkhomenko, Egor Silvestrov, Ilia Trushkin, Ilia Vasiliev, Ivan Kirillov, Ivan Mikheev, Kirill Chernyshev, Kirill Malakhov, Konstantin Zakharov, Valeriya Kobenko","submitted_at":"2026-08-06T09:34:00Z","abstract_excerpt":"Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05798","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/2608.05798/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-07T00:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rOQrxSpGwMlZoLZEHfDHRVuwOUEkRYJqgy3GB3pfbrfSew8k2bxLltlgtqmp7GfDZmSXAogp6nocEwbMKt0cBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:42:42.360418Z"},"content_sha256":"2f045b51794213c0dbdc9bf05636adf13c59d3a712300e8d30c408253d7c14ff","schema_version":"1.0","event_id":"sha256:2f045b51794213c0dbdc9bf05636adf13c59d3a712300e8d30c408253d7c14ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RKTK473JJSFLO7XS4YGUQKZBB/bundle.json","state_url":"https://pith.science/pith/7RKTK473JJSFLO7XS4YGUQKZBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RKTK473JJSFLO7XS4YGUQKZBB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:42:42Z","links":{"resolver":"https://pith.science/pith/7RKTK473JJSFLO7XS4YGUQKZBB","bundle":"https://pith.science/pith/7RKTK473JJSFLO7XS4YGUQKZBB/bundle.json","state":"https://pith.science/pith/7RKTK473JJSFLO7XS4YGUQKZBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RKTK473JJSFLO7XS4YGUQKZBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7RKTK473JJSFLO7XS4YGUQKZBB","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":"6a166dd82ddf7c53fab640ee67186f1a8905db724891e0e8d6dcbcea01526d74","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:34:00Z","title_canon_sha256":"29a7eeee6efefcd7d2f5662d0b614f4c5226e2283f5fc2a999f7c6b32d59486a"},"schema_version":"1.0","source":{"id":"2608.05798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05798","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05798v1","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05798","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"7RKTK473JJSF","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"7RKTK473JJSFLO7X","created_at":"2026-08-07T00:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"7RKTK473","created_at":"2026-08-07T00:52:46Z"}],"graph_snapshots":[{"event_id":"sha256:2f045b51794213c0dbdc9bf05636adf13c59d3a712300e8d30c408253d7c14ff","target":"graph","created_at":"2026-08-07T00:52:46Z","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/2608.05798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 c","authors_text":"Alexander Ivanov, Andrey Shutkin, Azat Saginbaev, David Chikovani, Denis Parkhomenko, Egor Silvestrov, Ilia Trushkin, Ilia Vasiliev, Ivan Kirillov, Ivan Mikheev, Kirill Chernyshev, Kirill Malakhov, Konstantin Zakharov, Valeriya Kobenko","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:34:00Z","title":"KVAE: Family of Tokenizers for Multimodal Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05798","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:df7e503805ed8339c63604e4d1cb2a6a341a715bfce7e3ee829c2d00dc61698c","target":"record","created_at":"2026-08-07T00:52:46Z","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":"6a166dd82ddf7c53fab640ee67186f1a8905db724891e0e8d6dcbcea01526d74","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-06T09:34:00Z","title_canon_sha256":"29a7eeee6efefcd7d2f5662d0b614f4c5226e2283f5fc2a999f7c6b32d59486a"},"schema_version":"1.0","source":{"id":"2608.05798","kind":"arxiv","version":1}},"canonical_sha256":"fc553573fb4a6455bbf797306a41590864f8deadc9f0cca15761176437ea0049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc553573fb4a6455bbf797306a41590864f8deadc9f0cca15761176437ea0049","first_computed_at":"2026-08-07T00:52:46.382099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:52:46.382099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xVc2AaKePxAY95O4BH+0TafZUdnSff9hVRg42NTTBhNHbKooeQYADzMlwZozjITNd+TnnzlupWRHKsVgFmd/AA==","signature_status":"signed_v1","signed_at":"2026-08-07T00:52:46.383599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df7e503805ed8339c63604e4d1cb2a6a341a715bfce7e3ee829c2d00dc61698c","sha256:2f045b51794213c0dbdc9bf05636adf13c59d3a712300e8d30c408253d7c14ff"],"state_sha256":"1e09b88b30fa1166fec477342a8eaf6fbc2177bb1e98cd6e479f605596ef91d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNd91GhGKYT1ChxcfPAstGf/5T93nn830Ak7JkemRsJoAWcHpChfHGAVfvKrshy6g/6KBkAskJyhSXJg1MvQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:42:42.364798Z","bundle_sha256":"bb1261ae4fdb1aa67792588d6712bedfc31af4209c966763cc2e51bffae7ff9a"}}