{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HXSYQGJYUAQDF35PNPRS33LULW","short_pith_number":"pith:HXSYQGJY","canonical_record":{"source":{"id":"2507.13264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T16:17:37Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1c9995064ec580e29eaf141045398ed1722704da2f7528f31a597ae89a32321a","abstract_canon_sha256":"8148ee9d7958f8841199fa8750563f20ed5bfaa24bd90cef359307626cad32f3"},"schema_version":"1.0"},"canonical_sha256":"3de5881938a02032efaf6be32ded745d9e1debb33dc7d35e1f6beaacf2f705a5","source":{"kind":"arxiv","id":"2507.13264","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13264","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13264v1","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13264","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"HXSYQGJYUAQD","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"HXSYQGJYUAQDF35P","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"HXSYQGJY","created_at":"2026-07-05T11:38:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HXSYQGJYUAQDF35PNPRS33LULW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T16:17:37Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1c9995064ec580e29eaf141045398ed1722704da2f7528f31a597ae89a32321a","abstract_canon_sha256":"8148ee9d7958f8841199fa8750563f20ed5bfaa24bd90cef359307626cad32f3"},"schema_version":"1.0"},"canonical_sha256":"3de5881938a02032efaf6be32ded745d9e1debb33dc7d35e1f6beaacf2f705a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:58.168283Z","signature_b64":"6+hjN66/wqEILi+K73cbdtCqxC2iDP9XdkYR2qBZCnyIso3Z+lcK0KE8/Yk1qOTQCsP7qcj2luGDIhtaV3ngDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3de5881938a02032efaf6be32ded745d9e1debb33dc7d35e1f6beaacf2f705a5","last_reissued_at":"2026-07-05T11:38:58.167795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:58.167795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13264","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":"2026-07-05T11:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUdvqS296uaWKWfEGHsgxB/tB423LEq3OLhSDtCYwReMiZTReYqzNTmUuqD5Fx7HbhufGaX7Uyz+ZK1PCDAlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:42:43.982188Z"},"content_sha256":"7a90eca6c0de097f1951f1bdb63e06b48a32e3184a9062c12718aee6ee02d1d2","schema_version":"1.0","event_id":"sha256:7a90eca6c0de097f1951f1bdb63e06b48a32e3184a9062c12718aee6ee02d1d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HXSYQGJYUAQDF35PNPRS33LULW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voxtral","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexander H. Liu, Alexandre Sablayrolles, Am\\'elie H\\'eliou, Am\\'elie Martin, Andy Ehrenberg, Andy Lo, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozi\\`ere, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Cl\\'emence Lanfranchi, Cl\\'ement Denoix, Corentin Barreau, Darius Dabert, Devendra Singh Chaplot, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gabrielle Berrada, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Lample, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jason Rute, Jean-Hadrien Chabran, Jean-Malo Delignon, Jessica Chudnovsky, Joachim Studnia, Joep Barmentlo, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Karmesh Yadav, Kartik Khandelwal, Khyathi Raghavi Chandu, Kush Jain, L\\'elio Renard Lavaud, L\\'eonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Matthieu Dinot, Maxime Darrin, Maximilian Augustin, Micka\\\"el Seznec, Neha Gupta, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patrick von Platen, Patryk Saffer, Paula Kurylowicz, Paul Jacob, Paul Wambergue, Pavankumar Reddy Muddireddy, Philom\\`ene Chagniot, Pierre Stock, Pravesh Agrawal, R\\'emi Delacourt, Romain Sauvestre, Roman Soletskyi, Sagar Vaze, Sanchit Gandhi, Sandeep Subramanian, Saurabh Garg, Shashwat Dalal, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Foubert, Thomas Robert, Thomas Wang, Timoth\\'ee Lacroix, Tom Bewley, Valeriia Nemychnikova, Victor Paltz, Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yihan Wan, Yunhao Tang","submitted_at":"2025-07-17T16:17:37Z","abstract_excerpt":"We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art performance across a diverse range of audio benchmarks, while preserving strong text capabilities. Voxtral Small outperforms a number of closed-source models, while being small enough to run locally. A 32K context window enables the model to handle audio files up to 40 minutes in duration and long multi-turn conversations. We also contribute three benchmarks for evaluating speech understanding models on knowledge and triv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13264","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/2507.13264/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":"2026-07-05T11:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgNeI0UvN7e+aQn+mr1aN9vMbGRcTMRkgYDifBOGhdEZUjdA46OI+tzs9PF+5aEvHRJLzsXLANmkJSBmyxBkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:42:43.982593Z"},"content_sha256":"5498c0275dbd1ee515ec3479da4d8a6f0f62fde936657570e64c528a7ec9ea7b","schema_version":"1.0","event_id":"sha256:5498c0275dbd1ee515ec3479da4d8a6f0f62fde936657570e64c528a7ec9ea7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXSYQGJYUAQDF35PNPRS33LULW/bundle.json","state_url":"https://pith.science/pith/HXSYQGJYUAQDF35PNPRS33LULW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXSYQGJYUAQDF35PNPRS33LULW/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":"2026-07-07T09:42:43Z","links":{"resolver":"https://pith.science/pith/HXSYQGJYUAQDF35PNPRS33LULW","bundle":"https://pith.science/pith/HXSYQGJYUAQDF35PNPRS33LULW/bundle.json","state":"https://pith.science/pith/HXSYQGJYUAQDF35PNPRS33LULW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXSYQGJYUAQDF35PNPRS33LULW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HXSYQGJYUAQDF35PNPRS33LULW","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":"8148ee9d7958f8841199fa8750563f20ed5bfaa24bd90cef359307626cad32f3","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T16:17:37Z","title_canon_sha256":"1c9995064ec580e29eaf141045398ed1722704da2f7528f31a597ae89a32321a"},"schema_version":"1.0","source":{"id":"2507.13264","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13264","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13264v1","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13264","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"HXSYQGJYUAQD","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"HXSYQGJYUAQDF35P","created_at":"2026-07-05T11:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"HXSYQGJY","created_at":"2026-07-05T11:38:58Z"}],"graph_snapshots":[{"event_id":"sha256:5498c0275dbd1ee515ec3479da4d8a6f0f62fde936657570e64c528a7ec9ea7b","target":"graph","created_at":"2026-07-05T11:38:58Z","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/2507.13264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art performance across a diverse range of audio benchmarks, while preserving strong text capabilities. Voxtral Small outperforms a number of closed-source models, while being small enough to run locally. A 32K context window enables the model to handle audio files up to 40 minutes in duration and long multi-turn conversations. We also contribute three benchmarks for evaluating speech understanding models on knowledge and triv","authors_text":"Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexander H. Liu, Alexandre Sablayrolles, Am\\'elie H\\'eliou, Am\\'elie Martin, Andy Ehrenberg, Andy Lo, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozi\\`ere, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Cl\\'emence Lanfranchi, Cl\\'ement Denoix, Corentin Barreau, Darius Dabert, Devendra Singh Chaplot, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gabrielle Berrada, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Lample, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jason Rute, Jean-Hadrien Chabran, Jean-Malo Delignon, Jessica Chudnovsky, Joachim Studnia, Joep Barmentlo, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Karmesh Yadav, Kartik Khandelwal, Khyathi Raghavi Chandu, Kush Jain, L\\'elio Renard Lavaud, L\\'eonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Matthieu Dinot, Maxime Darrin, Maximilian Augustin, Micka\\\"el Seznec, Neha Gupta, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patrick von Platen, Patryk Saffer, Paula Kurylowicz, Paul Jacob, Paul Wambergue, Pavankumar Reddy Muddireddy, Philom\\`ene Chagniot, Pierre Stock, Pravesh Agrawal, R\\'emi Delacourt, Romain Sauvestre, Roman Soletskyi, Sagar Vaze, Sanchit Gandhi, Sandeep Subramanian, Saurabh Garg, Shashwat Dalal, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Foubert, Thomas Robert, Thomas Wang, Timoth\\'ee Lacroix, Tom Bewley, Valeriia Nemychnikova, Victor Paltz, Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yihan Wan, Yunhao Tang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T16:17:37Z","title":"Voxtral"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13264","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":"sha256:7a90eca6c0de097f1951f1bdb63e06b48a32e3184a9062c12718aee6ee02d1d2","target":"record","created_at":"2026-07-05T11:38:58Z","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":"8148ee9d7958f8841199fa8750563f20ed5bfaa24bd90cef359307626cad32f3","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T16:17:37Z","title_canon_sha256":"1c9995064ec580e29eaf141045398ed1722704da2f7528f31a597ae89a32321a"},"schema_version":"1.0","source":{"id":"2507.13264","kind":"arxiv","version":1}},"canonical_sha256":"3de5881938a02032efaf6be32ded745d9e1debb33dc7d35e1f6beaacf2f705a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3de5881938a02032efaf6be32ded745d9e1debb33dc7d35e1f6beaacf2f705a5","first_computed_at":"2026-07-05T11:38:58.167795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:58.167795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6+hjN66/wqEILi+K73cbdtCqxC2iDP9XdkYR2qBZCnyIso3Z+lcK0KE8/Yk1qOTQCsP7qcj2luGDIhtaV3ngDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:58.168283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13264","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a90eca6c0de097f1951f1bdb63e06b48a32e3184a9062c12718aee6ee02d1d2","sha256:5498c0275dbd1ee515ec3479da4d8a6f0f62fde936657570e64c528a7ec9ea7b"],"state_sha256":"95934027f01ff2b8acdd8a7e440f8f0f8f5d5548ea068cd33defff7c9e781c94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I2hBWWrs578mFuQNltDYbSvzqoMFblAs/IkYT3bK1i4sO2bR3XyMvfKPz8IhwyZidCaZJsbwx09PnLmmsGyUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:42:43.984619Z","bundle_sha256":"21b905dbcf747c7c0250ee525e7ed10369394a57bd88e96c63ab1752e4bee451"}}