{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3Z7XKTDTNXMZMYOOA564ZPX34A","short_pith_number":"pith:3Z7XKTDT","canonical_record":{"source":{"id":"2412.04261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T15:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"506b23a3282c5af900db5fdfd35ce19325d52a8580915e4d2424a335a6f3f27f","abstract_canon_sha256":"e8ef5045c9091dfee9ee3083a4ce6d42a167ade2f3415b913610b25225a5346d"},"schema_version":"1.0"},"canonical_sha256":"de7f754c736dd99661ce077dccbefbe02a2e16ae1970a8de88dee89001618ebb","source":{"kind":"arxiv","id":"2412.04261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04261","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04261v1","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04261","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_12","alias_value":"3Z7XKTDTNXMZ","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_16","alias_value":"3Z7XKTDTNXMZMYOO","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_8","alias_value":"3Z7XKTDT","created_at":"2026-07-05T09:45:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3Z7XKTDTNXMZMYOOA564ZPX34A","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T15:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"506b23a3282c5af900db5fdfd35ce19325d52a8580915e4d2424a335a6f3f27f","abstract_canon_sha256":"e8ef5045c9091dfee9ee3083a4ce6d42a167ade2f3415b913610b25225a5346d"},"schema_version":"1.0"},"canonical_sha256":"de7f754c736dd99661ce077dccbefbe02a2e16ae1970a8de88dee89001618ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:01.662086Z","signature_b64":"SOhNPVHCETFlKJoawJp/7uOqLdA1W07RZclEzEQcxAx35e0cbXFTqmZ/R6V5SJ64G1rGg1GeWpXI4/km1ofLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de7f754c736dd99661ce077dccbefbe02a2e16ae1970a8de88dee89001618ebb","last_reissued_at":"2026-07-05T09:45:01.661505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:01.661505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04261","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":"2026-07-05T09:45:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HWkUAIdRyicOmwvhM6WVu0omnIJFDf9Z9UlwnmNv51dxKfr5HTUcgiHrXhaZusKkOpUcKzhwrhWLLAcW+PKVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:52:06.190190Z"},"content_sha256":"7f4a64cc5a62db59cf115959d1b3468796d6b7bee127deca6020362d1d3f962a","schema_version":"1.0","event_id":"sha256:7f4a64cc5a62db59cf115959d1b3468796d6b7bee127deca6020362d1d3f962a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3Z7XKTDTNXMZMYOOA564ZPX34A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Adrien Morisot, Ahmet \\\"Ust\\\"un, Aidan Gomez, Aidan Peppin, Alejandro Salamanca, Aleksandra Piktus, Amir Shukayev, Arash Ahmadian, Beyza Ermis, Bharat Venkitesh, Bowen Yang, Daniel D'souza, David Cairuz, Dwarak Talupuru, Eddie Kim, Felipe Cruz-Salinas, Florian Strub, Hangyu Lin, Ivan Zhang, John Dang, Jon Ander Campos, Lucas Crawhall-Stein, Madeline Smith, Manoj Govindassamy, Marzieh Fadaee, Meor Amer, Nathan Grinsztajn, Nick Frosst, Phil Blunsom, Roman Castagn\\'e, Sammie Bae, Sandra Kublik, Sara Hooker, Shivalika Singh, Sudip Roy, Sungjin Hong, Sylvie Shang Shi, Terrence Zhao, Tim Chung, Tom Kocmi, Viraat Aryabumi, Wei-Yin Ko, Yannis Flet-Berliac, Yi-Chern Tan","submitted_at":"2024-12-05T15:41:06Z","abstract_excerpt":"We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models. By leveraging several years of research at Cohere For AI and Cohere, including advancements in data arbitrage, multilingual preference training, and model merging, Aya Expanse sets a new state-of-the-art in multilingual performance. Our evaluations on the Arena-Hard-Auto dataset, translated into 23 languages, demonstrate that Aya"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04261","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/2412.04261/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":"2026-07-05T09:45:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMbQlVN/vAI0F4Dexdk2h7FDLxjcGd5l5ZVga1+vFDc8ngpxEgHeYFIz16la51Ju6JKtCfF3E1mYYi5TqwHgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:52:06.190589Z"},"content_sha256":"db6e8562d83db29fc45f58e6c54b861c621ee13123c76b8cdb06fe3cad1b3379","schema_version":"1.0","event_id":"sha256:db6e8562d83db29fc45f58e6c54b861c621ee13123c76b8cdb06fe3cad1b3379"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/bundle.json","state_url":"https://pith.science/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/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":"2026-07-07T04:52:06Z","links":{"resolver":"https://pith.science/pith/3Z7XKTDTNXMZMYOOA564ZPX34A","bundle":"https://pith.science/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/bundle.json","state":"https://pith.science/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3Z7XKTDTNXMZMYOOA564ZPX34A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3Z7XKTDTNXMZMYOOA564ZPX34A","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":"e8ef5045c9091dfee9ee3083a4ce6d42a167ade2f3415b913610b25225a5346d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T15:41:06Z","title_canon_sha256":"506b23a3282c5af900db5fdfd35ce19325d52a8580915e4d2424a335a6f3f27f"},"schema_version":"1.0","source":{"id":"2412.04261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04261","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04261v1","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04261","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_12","alias_value":"3Z7XKTDTNXMZ","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_16","alias_value":"3Z7XKTDTNXMZMYOO","created_at":"2026-07-05T09:45:01Z"},{"alias_kind":"pith_short_8","alias_value":"3Z7XKTDT","created_at":"2026-07-05T09:45:01Z"}],"graph_snapshots":[{"event_id":"sha256:db6e8562d83db29fc45f58e6c54b861c621ee13123c76b8cdb06fe3cad1b3379","target":"graph","created_at":"2026-07-05T09:45:01Z","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/2412.04261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly performant multilingual models that match or surpass the capabilities of monolingual models. By leveraging several years of research at Cohere For AI and Cohere, including advancements in data arbitrage, multilingual preference training, and model merging, Aya Expanse sets a new state-of-the-art in multilingual performance. Our evaluations on the Arena-Hard-Auto dataset, translated into 23 languages, demonstrate that Aya","authors_text":"Acyr Locatelli, Adrien Morisot, Ahmet \\\"Ust\\\"un, Aidan Gomez, Aidan Peppin, Alejandro Salamanca, Aleksandra Piktus, Amir Shukayev, Arash Ahmadian, Beyza Ermis, Bharat Venkitesh, Bowen Yang, Daniel D'souza, David Cairuz, Dwarak Talupuru, Eddie Kim, Felipe Cruz-Salinas, Florian Strub, Hangyu Lin, Ivan Zhang, John Dang, Jon Ander Campos, Lucas Crawhall-Stein, Madeline Smith, Manoj Govindassamy, Marzieh Fadaee, Meor Amer, Nathan Grinsztajn, Nick Frosst, Phil Blunsom, Roman Castagn\\'e, Sammie Bae, Sandra Kublik, Sara Hooker, Shivalika Singh, Sudip Roy, Sungjin Hong, Sylvie Shang Shi, Terrence Zhao, Tim Chung, Tom Kocmi, Viraat Aryabumi, Wei-Yin Ko, Yannis Flet-Berliac, Yi-Chern Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T15:41:06Z","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04261","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":"sha256:7f4a64cc5a62db59cf115959d1b3468796d6b7bee127deca6020362d1d3f962a","target":"record","created_at":"2026-07-05T09:45:01Z","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":"e8ef5045c9091dfee9ee3083a4ce6d42a167ade2f3415b913610b25225a5346d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T15:41:06Z","title_canon_sha256":"506b23a3282c5af900db5fdfd35ce19325d52a8580915e4d2424a335a6f3f27f"},"schema_version":"1.0","source":{"id":"2412.04261","kind":"arxiv","version":1}},"canonical_sha256":"de7f754c736dd99661ce077dccbefbe02a2e16ae1970a8de88dee89001618ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de7f754c736dd99661ce077dccbefbe02a2e16ae1970a8de88dee89001618ebb","first_computed_at":"2026-07-05T09:45:01.661505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:01.661505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOhNPVHCETFlKJoawJp/7uOqLdA1W07RZclEzEQcxAx35e0cbXFTqmZ/R6V5SJ64G1rGg1GeWpXI4/km1ofLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:01.662086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f4a64cc5a62db59cf115959d1b3468796d6b7bee127deca6020362d1d3f962a","sha256:db6e8562d83db29fc45f58e6c54b861c621ee13123c76b8cdb06fe3cad1b3379"],"state_sha256":"065458166389bc6e923a1ba546fb872e77cc92cea41e1fd9c148179c06495159"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+iUYtOvnBopAmvxjCVkiugX2uPM1N9x6kbaOEvQp/LaQNEgm72xTaaAF9poGIAXEyGlT0BbRtzIRb48OSDKTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:52:06.192841Z","bundle_sha256":"c219abb63e9472ab50268aeea239959509171e4ad085f74c98ab72872ae562df"}}