{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7CFUCMRWMCV26EVN66IYTWTNJB","short_pith_number":"pith:7CFUCMRW","canonical_record":{"source":{"id":"2211.05100","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T18:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"4e5fb9fbaefc58fa6703b8412964dfdb31658278632b938bb57a81956a15579a","abstract_canon_sha256":"a91614a2148a6d8f971656f499d525ac14b911ee834764a20de434812533328d"},"schema_version":"1.0"},"canonical_sha256":"f88b41323660abaf12adf79189da6d48403d30888eb19042b14b57ac997206a2","source":{"kind":"arxiv","id":"2211.05100","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05100","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05100v4","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05100","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_12","alias_value":"7CFUCMRWMCV2","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_16","alias_value":"7CFUCMRWMCV26EVN","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_8","alias_value":"7CFUCMRW","created_at":"2026-07-05T06:24:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7CFUCMRWMCV26EVN66IYTWTNJB","target":"record","payload":{"canonical_record":{"source":{"id":"2211.05100","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T18:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"4e5fb9fbaefc58fa6703b8412964dfdb31658278632b938bb57a81956a15579a","abstract_canon_sha256":"a91614a2148a6d8f971656f499d525ac14b911ee834764a20de434812533328d"},"schema_version":"1.0"},"canonical_sha256":"f88b41323660abaf12adf79189da6d48403d30888eb19042b14b57ac997206a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:47.063293Z","signature_b64":"Ksq4nHjhUy1q++Q9i3jPj7Xm9t9R2jdC62/ZZODw3QtPu+Np3tlBuBeMgLLhPfEfPwoJzhTfvYGIp412M9B+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f88b41323660abaf12adf79189da6d48403d30888eb19042b14b57ac997206a2","last_reissued_at":"2026-07-05T06:24:47.062628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:47.062628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.05100","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:24:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27Ke28S04N+GdYkLLXHEFCs0M+vNeBXHWw1dAMBEHVoiOlmYFUX8ZeqP4+ZBkV0LABrKGaiezpX3sCTgCXXkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:38:32.099613Z"},"content_sha256":"d172a15354c6ba3dfcd3c447056fb42152760aba37bdf0262304f4df80f7819d","schema_version":"1.0","event_id":"sha256:d172a15354c6ba3dfcd3c447056fb42152760aba37bdf0262304f4df80f7819d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7CFUCMRWMCV26EVN66IYTWTNJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Gokaslan, Abheesht Sharma, Abhinav Ramesh Kashyap, Adam Roberts, Adi Simhi, Ahmed Baruwa, Aitor Soroa, Albert Villanova del Moral, Albert Webson, Alexander M. Rush, Alexandra Sasha Luccioni, Alfredo Palasciano, Alham Fikri Aji, Alice Rueda, Alison Callahan, Amanda Pestana, Amanpreet Singh, Amir Feizpour, Amit Alfassy, Ammar Khan, Amy Faranak, Ana Santos, Anastasia Cheveleva, Andrea Santilli, Angela Fan, Angelina McMillan-Major, Anima Shukla, Anna Rogers, Anne-Laure Ligozat, Anthony Hevia, Antigona Unldreaj, Antoine Chaffin, Antonio Miranda-Escalada, Arash Aghagol, Arezoo Abdollahi, Ariel Kreisberg Nitzav, Arjun Subramonian, Arnaud Stiegler, Arun Raja, Aur\\'elie N\\'ev\\'eol, Aycha Tammour, Ayush Singh, Azadeh HajiHosseini, Bahareh Behroozi, Benjamin Ajibade, Benjamin Beilharz, Benjamin Heinzerling, Beno\\^it Sagot, Bharat Saxena, BigScience Workshop: Teven Le Scao, Bo Wang, Caio Brito, Canwen Xu, Carlos Mu\\~noz Ferrandis, Charles Lovering, Chenghao Mou, Chenglei Si, Chenxi Zhou, Chirag Jain, Chris Emezue, Christopher Akiki, Christopher Klamm, Chuxin Xu, Cl\\'ementine Fourrier, Colin Leong, Colin Raffel, Conglong Li, Dan Garrette, Daniel Hesslow, Daniel Le\\'on Peri\\~n\\'an, Daniel McDuff, Daniel Molano, Daniel van Strien, Danish Contractor, David Ifeoluwa Adelani, David Lansky, Davis David, Davut Emre Ta\\c{s}ar, Debajyoti Datta, Deepak Narayanan, Deepak Tunuguntla, Dian Yu, Douwe Kiela, Dragomir Radev, Duong A. Nguyen, Eduardo Gonz\\'alez Ponferrada, Edward Tan, Efrat Levkovizh, Ehud Reiter, Ekaterina Taktasheva, Ekaterina Voloshina, Eli Bogdanov, Elizabeth Salesky, Eliza Szczechla, Ellie Pavlick, Emi Baylor, Enrique Manjavacas, Ethan Kim, Eyal Bar Natan, Ezinwanne Ozoani, Fabio Barth, Fatima Mirza, Florian Fuhrimann, Fran\\c{c}ois Yvon, Francesco De Toni, Frankline Ononiwu, Gabriel Altay, Genta Indra Winata, G\\'erard Dupont, Germ\\'an Kruszewski, Giada Pistilli, Giyaseddin Bayrak, Gully Burns, Gunjan Chhablani, Habib Rezanejad, Hadar Tojarieh, Hady Elsahar, Hailey Schoelkopf, Hamza Benyamina, Han Wang, Harshit Pandey, Hatim Bourfoune, Helena U. Vrabec, Hendrik Strobelt, Hessie Jones, Hieu Tran, Hugo Lauren\\c{c}on, Huu Nguyen, Hyung Won Chung, Ian Yu, Idris Abdulmumin, Imane Bello, Indrani Bhattacharya, Irene Solaiman, Irina Sedenko, Isaac Johnson, Isar Nejadgholi, Ishani Dash, Itziar Gonzalez-Dios, Iz Beltagy, Jaesung Tae, Jan-Christoph Kalo, Jared Casper, Jason Alan Fries, Jason Phang, Javier de la Rosa, Jeff Rasley, Jekaterina Novikova, Jenny Chim, Jesse Dodge, Jesse Passmore, Jessica Zosa Forde, Jian Zhu, Jihyun Kang, John Giorgi, Jonas Golde, Jonathan Chang, Jonathan Tow, Jordan Clive, J\\\"org Frohberg, Jose David Posada, Joseph Tobing, Josh Seltzer, Jos Rozen, Joydeep Bhattacharjee, Julien Launay, Julio Bonis Sanz, Jungo Kasai, Karthik Rangasai Sivaraman, Ken Kawamura, Khalid Almubarak, Kimbo Chen, Kyle Lo, Leandro Von Werra, Leo Gao, Leon Weber, Liam Hazan, Lintang Sutawika, Livia Dutra, Lokesh Bulchandani, Long Phan, Loubna Ben Allal, Lucile Saulnier, Ludovic Tanguy, Luisa Shinzato, Lu Liu, Madeleine Hahn de Bykhovetz, Maged S. Al-shaibani, Maiko Takeuchi, Mairon Samagaio, Manan Dey, Manuel Romero Mu\\~noz, Maraim Elbadri, Maraim Masoud, Marc P\\`amies, Margaret Mitchell, Margot Mieskes, Maria A Castillo, Mar\\'ia Grandury, Marianna Nezhurina, Marine Carpuat, Mario S\\\"anger, Mario \\v{S}a\\v{s}ko, Marissa Gerchick, Martha Akinlolu, Mathilde Bras, Matteo Manica, Matthias Gall\\'e, Matthias Samwald, Max Huang, Maximin Coavoux, Max Ryabinin, Mayank Mishra, Mayank Singh, Michael Cullan, Michael McKenna, Michael Weinberg, Michiel De Wolf, Mike Qiu, Mike Tian-Jian Jiang, Mina Mihaljcic, Minh Chien Vu, Minjia Zhang, Minna Liu, Miruna Clinciu, Mohammad A. Jauhar, Mohammad Shoeybi, Moritz Freidank, M Saiful Bari, Muhammed Ghauri, Mustafa Ghaleb, Mykola Burynok, Myriam Peyrounette, Myungsun Kang, Nafis Abrar, Najoung Kim, Natasha Seelam, Nathan Dahlberg, Nazneen Rajani, Newton Cheng, Nicholas Michio Broad, Nicolas Patry, Nihal Nayak, Niklas Muennighoff, Nikolaus Muellner, Nishant Subramani, Nora Kassner, Nouamane Tazi, Nour Elkott, Nour Fahmy, Nurulaqilla Khamis, Ofir Press, Olanrewaju Samuel, Olatunji Ruwase, Oleg Serikov, Olivier Nguyen, Omar Espejel, Omar Sanseviero, Omer Antverg, Ona de Gibert, Oskar van der Wal, Pascale Fung, Patrick Haller, Patrick von Platen, Paulo Villegas, Pawan Sasanka Ammanamanchi, Pedro Ortiz Suarez, Peter Henderson, Pierre Colombo, Pierre Cornette, Pierre Fran\\c{c}ois Lavall\\'ee, Priscilla Amuok, Quentin Lhoest, Rachel Bawden, Ramya Chandrasekhar, Ran An, Rasmus Kromann, R\\'emi Lacroix, Renata Eisenberg, Rheza Harliman, Rishi Bommasani, Robert Martin, Roberto Luis L\\'opez, Rodrigo Canalli, Roman Castagn\\'e, Rosaline Su, Rui Ribeiro, Ruisi Su, Rui Zhang, Ruochen Zhang, Ryan Hao, Ryan Teehan, Sabrina J. Mielke, Salomey Osei, Samira Alizadeh, Sampo Pyysalo, Samson Tan, Samuel Albanie, Samuel Cahyawijaya, Samuele Garda, Samyam Rajbhandari, Sanchit Gandhi, Sarmad Shubber, Sebastian Gehrmann, Sebastian Nagel, Shachar Mirkin, Shaden Smith, Shaked Brody, Shamik Bose, Shamsuddeen Hassan Muhammad, Shani Pais, Shanya Sharma, Shayne Longpre, Sheng Shen, Shlok S Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Silas Wang, Simon Ott, Sinee Sang-aroonsiri, Somaieh Nikpoor, Sourav Roy, Srishti Kumar, Srulik Ben-David, Stanislav Silberberg, Stas Bekman, Stefan Schweter, Stella Biderman, St\\'ephane Requena, Stephen H. Bach, Suhas Pai, Suraj Patil, Sushil Bharati, Suzana Ili\\'c, Sydney Zink, Sylvain Viguier, Taewoon Kim, Tali Bers, Tanmay Laud, Tatiana Shavrina, Thanh Le, Th\\'eo Gigant, Thibault Fevry, Thomas Scialom, Thomas Wang, Thomas Wolf, Tiago Timponi Torrent, Tian Yun, Tim Dettmers, Timo Schick, Tobi Oyebade, Tomasz Limisiewicz, Tomoya Kainuma, Trieu Le, Trishala Neeraj, Tristan Thrush, Urmish Thakker, Valentin Danchev, Vassilina Nikoulina, Verena Rieser, Veronika Laippala, Victor Sanh, Vikas Raunak, Violette Lepercq, Vitaly Protasov, Vladislav Mikhailov, Vrinda Prabhu, Wilson Y. Lee, Wojciech Kusa, Xiangru Tang, Yacine Jernite, Yada Pruksachatkun, Yallow Uri, Yanis Labrak, Yash Shailesh Bajaj, Yash Venkatraman, Yifan Xu, Yingxin Xu, Yonatan Belinkov, Younes Belkada, Yoyo Yang, Yu Xu, Zachary Bamberger, Zach Nguyen, Zaid Alyafeai, Zden\\v{e}k Kasner, Zeerak Talat, Zheng-Xin Yong, Zhe Tan, Zhiqing Sun, Zhongli Xie, Zifan Ye","submitted_at":"2022-11-09T18:48:09Z","abstract_excerpt":"Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the unreported details of training procedure, data filtering, and benchmark evaluation setup produce generalizable capabilities rather than benchmark-specific artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a525bfc37f1bdfc146976cce17489a4f430d1abdcc8b79f984530bbfa29fb143"},"source":{"id":"2211.05100","kind":"arxiv","version":4},"verdict":{"id":"1867d87f-ff1b-4e51-9042-b1abf1f16c2c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T00:38:59.003626Z","strongest_claim":"BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning.","one_line_summary":"BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the unreported details of training procedure, data filtering, and benchmark evaluation setup produce generalizable capabilities rather than benchmark-specific artifacts.","pith_extraction_headline":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.05100/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":249,"sample":[{"doi":"","year":null,"title":"Exploring BERT's Vocabulary , author =","work_id":"605ddbd8-95a1-46a3-acf7-9f76dbef11ba","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the AAAI conference on artificial intelligence , year =","work_id":"950f62ee-f6ad-4583-b7a3-a5f5abc211cd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Conference on Learning Representations , year=","work_id":"f7101c0a-5c39-4c12-b861-e59c16d6b22b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3278721.3278729","year":2018,"title":"2018 , isbn =","work_id":"34eca032-d4af-4ba4-b657-d90a486e2c1b","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/n18-2003","year":2018,"title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","work_id":"debd34b6-f412-41f5-8776-18ca1afb906a","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":249,"snapshot_sha256":"7e71e193cc11e2c0463df7ba363e2de37d26c3f44175f3f4a352a28d43d7a012","internal_anchors":25},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fe8e262bbaa643bbc708d130550e711f09a04b87caa8b25a7ec4b9ae9984cd16"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1867d87f-ff1b-4e51-9042-b1abf1f16c2c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:24:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+ImomhPU91mwWqLu3Bxay7lEmiRfjDAfDcGd4lo03v8wfrF87aqimExBZ6BT7VqJnGzTE+L1rDmB1PtpWqxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:38:32.100609Z"},"content_sha256":"22d04efc637257ceae80c032f549a1a08703bcc41d636b6aa1e0c29cc822f1bd","schema_version":"1.0","event_id":"sha256:22d04efc637257ceae80c032f549a1a08703bcc41d636b6aa1e0c29cc822f1bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CFUCMRWMCV26EVN66IYTWTNJB/bundle.json","state_url":"https://pith.science/pith/7CFUCMRWMCV26EVN66IYTWTNJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CFUCMRWMCV26EVN66IYTWTNJB/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":"2026-08-03T21:38:32Z","links":{"resolver":"https://pith.science/pith/7CFUCMRWMCV26EVN66IYTWTNJB","bundle":"https://pith.science/pith/7CFUCMRWMCV26EVN66IYTWTNJB/bundle.json","state":"https://pith.science/pith/7CFUCMRWMCV26EVN66IYTWTNJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CFUCMRWMCV26EVN66IYTWTNJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7CFUCMRWMCV26EVN66IYTWTNJB","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":"a91614a2148a6d8f971656f499d525ac14b911ee834764a20de434812533328d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T18:48:09Z","title_canon_sha256":"4e5fb9fbaefc58fa6703b8412964dfdb31658278632b938bb57a81956a15579a"},"schema_version":"1.0","source":{"id":"2211.05100","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05100","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05100v4","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05100","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_12","alias_value":"7CFUCMRWMCV2","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_16","alias_value":"7CFUCMRWMCV26EVN","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_8","alias_value":"7CFUCMRW","created_at":"2026-07-05T06:24:47Z"}],"graph_snapshots":[{"event_id":"sha256:22d04efc637257ceae80c032f549a1a08703bcc41d636b6aa1e0c29cc822f1bd","target":"graph","created_at":"2026-07-05T06:24:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the unreported details of training procedure, data filtering, and benchmark evaluation setup produce generalizable capabilities rather than benchmark-specific artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly."}],"snapshot_sha256":"a525bfc37f1bdfc146976cce17489a4f430d1abdcc8b79f984530bbfa29fb143"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fe8e262bbaa643bbc708d130550e711f09a04b87caa8b25a7ec4b9ae9984cd16"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.05100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hu","authors_text":"Aaron Gokaslan, Abheesht Sharma, Abhinav Ramesh Kashyap, Adam Roberts, Adi Simhi, Ahmed Baruwa, Aitor Soroa, Albert Villanova del Moral, Albert Webson, Alexander M. Rush, Alexandra Sasha Luccioni, Alfredo Palasciano, Alham Fikri Aji, Alice Rueda, Alison Callahan, Amanda Pestana, Amanpreet Singh, Amir Feizpour, Amit Alfassy, Ammar Khan, Amy Faranak, Ana Santos, Anastasia Cheveleva, Andrea Santilli, Angela Fan, Angelina McMillan-Major, Anima Shukla, Anna Rogers, Anne-Laure Ligozat, Anthony Hevia, Antigona Unldreaj, Antoine Chaffin, Antonio Miranda-Escalada, Arash Aghagol, Arezoo Abdollahi, Ariel Kreisberg Nitzav, Arjun Subramonian, Arnaud Stiegler, Arun Raja, Aur\\'elie N\\'ev\\'eol, Aycha Tammour, Ayush Singh, Azadeh HajiHosseini, Bahareh Behroozi, Benjamin Ajibade, Benjamin Beilharz, Benjamin Heinzerling, Beno\\^it Sagot, Bharat Saxena, BigScience Workshop: Teven Le Scao, Bo Wang, Caio Brito, Canwen Xu, Carlos Mu\\~noz Ferrandis, Charles Lovering, Chenghao Mou, Chenglei Si, Chenxi Zhou, Chirag Jain, Chris Emezue, Christopher Akiki, Christopher Klamm, Chuxin Xu, Cl\\'ementine Fourrier, Colin Leong, Colin Raffel, Conglong Li, Dan Garrette, Daniel Hesslow, Daniel Le\\'on Peri\\~n\\'an, Daniel McDuff, Daniel Molano, Daniel van Strien, Danish Contractor, David Ifeoluwa Adelani, David Lansky, Davis David, Davut Emre Ta\\c{s}ar, Debajyoti Datta, Deepak Narayanan, Deepak Tunuguntla, Dian Yu, Douwe Kiela, Dragomir Radev, Duong A. Nguyen, Eduardo Gonz\\'alez Ponferrada, Edward Tan, Efrat Levkovizh, Ehud Reiter, Ekaterina Taktasheva, Ekaterina Voloshina, Eli Bogdanov, Elizabeth Salesky, Eliza Szczechla, Ellie Pavlick, Emi Baylor, Enrique Manjavacas, Ethan Kim, Eyal Bar Natan, Ezinwanne Ozoani, Fabio Barth, Fatima Mirza, Florian Fuhrimann, Fran\\c{c}ois Yvon, Francesco De Toni, Frankline Ononiwu, Gabriel Altay, Genta Indra Winata, G\\'erard Dupont, Germ\\'an Kruszewski, Giada Pistilli, Giyaseddin Bayrak, Gully Burns, Gunjan Chhablani, Habib Rezanejad, Hadar Tojarieh, Hady Elsahar, Hailey Schoelkopf, Hamza Benyamina, Han Wang, Harshit Pandey, Hatim Bourfoune, Helena U. Vrabec, Hendrik Strobelt, Hessie Jones, Hieu Tran, Hugo Lauren\\c{c}on, Huu Nguyen, Hyung Won Chung, Ian Yu, Idris Abdulmumin, Imane Bello, Indrani Bhattacharya, Irene Solaiman, Irina Sedenko, Isaac Johnson, Isar Nejadgholi, Ishani Dash, Itziar Gonzalez-Dios, Iz Beltagy, Jaesung Tae, Jan-Christoph Kalo, Jared Casper, Jason Alan Fries, Jason Phang, Javier de la Rosa, Jeff Rasley, Jekaterina Novikova, Jenny Chim, Jesse Dodge, Jesse Passmore, Jessica Zosa Forde, Jian Zhu, Jihyun Kang, John Giorgi, Jonas Golde, Jonathan Chang, Jonathan Tow, Jordan Clive, J\\\"org Frohberg, Jose David Posada, Joseph Tobing, Josh Seltzer, Jos Rozen, Joydeep Bhattacharjee, Julien Launay, Julio Bonis Sanz, Jungo Kasai, Karthik Rangasai Sivaraman, Ken Kawamura, Khalid Almubarak, Kimbo Chen, Kyle Lo, Leandro Von Werra, Leo Gao, Leon Weber, Liam Hazan, Lintang Sutawika, Livia Dutra, Lokesh Bulchandani, Long Phan, Loubna Ben Allal, Lucile Saulnier, Ludovic Tanguy, Luisa Shinzato, Lu Liu, Madeleine Hahn de Bykhovetz, Maged S. Al-shaibani, Maiko Takeuchi, Mairon Samagaio, Manan Dey, Manuel Romero Mu\\~noz, Maraim Elbadri, Maraim Masoud, Marc P\\`amies, Margaret Mitchell, Margot Mieskes, Maria A Castillo, Mar\\'ia Grandury, Marianna Nezhurina, Marine Carpuat, Mario S\\\"anger, Mario \\v{S}a\\v{s}ko, Marissa Gerchick, Martha Akinlolu, Mathilde Bras, Matteo Manica, Matthias Gall\\'e, Matthias Samwald, Max Huang, Maximin Coavoux, Max Ryabinin, Mayank Mishra, Mayank Singh, Michael Cullan, Michael McKenna, Michael Weinberg, Michiel De Wolf, Mike Qiu, Mike Tian-Jian Jiang, Mina Mihaljcic, Minh Chien Vu, Minjia Zhang, Minna Liu, Miruna Clinciu, Mohammad A. Jauhar, Mohammad Shoeybi, Moritz Freidank, M Saiful Bari, Muhammed Ghauri, Mustafa Ghaleb, Mykola Burynok, Myriam Peyrounette, Myungsun Kang, Nafis Abrar, Najoung Kim, Natasha Seelam, Nathan Dahlberg, Nazneen Rajani, Newton Cheng, Nicholas Michio Broad, Nicolas Patry, Nihal Nayak, Niklas Muennighoff, Nikolaus Muellner, Nishant Subramani, Nora Kassner, Nouamane Tazi, Nour Elkott, Nour Fahmy, Nurulaqilla Khamis, Ofir Press, Olanrewaju Samuel, Olatunji Ruwase, Oleg Serikov, Olivier Nguyen, Omar Espejel, Omar Sanseviero, Omer Antverg, Ona de Gibert, Oskar van der Wal, Pascale Fung, Patrick Haller, Patrick von Platen, Paulo Villegas, Pawan Sasanka Ammanamanchi, Pedro Ortiz Suarez, Peter Henderson, Pierre Colombo, Pierre Cornette, Pierre Fran\\c{c}ois Lavall\\'ee, Priscilla Amuok, Quentin Lhoest, Rachel Bawden, Ramya Chandrasekhar, Ran An, Rasmus Kromann, R\\'emi Lacroix, Renata Eisenberg, Rheza Harliman, Rishi Bommasani, Robert Martin, Roberto Luis L\\'opez, Rodrigo Canalli, Roman Castagn\\'e, Rosaline Su, Rui Ribeiro, Ruisi Su, Rui Zhang, Ruochen Zhang, Ryan Hao, Ryan Teehan, Sabrina J. Mielke, Salomey Osei, Samira Alizadeh, Sampo Pyysalo, Samson Tan, Samuel Albanie, Samuel Cahyawijaya, Samuele Garda, Samyam Rajbhandari, Sanchit Gandhi, Sarmad Shubber, Sebastian Gehrmann, Sebastian Nagel, Shachar Mirkin, Shaden Smith, Shaked Brody, Shamik Bose, Shamsuddeen Hassan Muhammad, Shani Pais, Shanya Sharma, Shayne Longpre, Sheng Shen, Shlok S Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Silas Wang, Simon Ott, Sinee Sang-aroonsiri, Somaieh Nikpoor, Sourav Roy, Srishti Kumar, Srulik Ben-David, Stanislav Silberberg, Stas Bekman, Stefan Schweter, Stella Biderman, St\\'ephane Requena, Stephen H. Bach, Suhas Pai, Suraj Patil, Sushil Bharati, Suzana Ili\\'c, Sydney Zink, Sylvain Viguier, Taewoon Kim, Tali Bers, Tanmay Laud, Tatiana Shavrina, Thanh Le, Th\\'eo Gigant, Thibault Fevry, Thomas Scialom, Thomas Wang, Thomas Wolf, Tiago Timponi Torrent, Tian Yun, Tim Dettmers, Timo Schick, Tobi Oyebade, Tomasz Limisiewicz, Tomoya Kainuma, Trieu Le, Trishala Neeraj, Tristan Thrush, Urmish Thakker, Valentin Danchev, Vassilina Nikoulina, Verena Rieser, Veronika Laippala, Victor Sanh, Vikas Raunak, Violette Lepercq, Vitaly Protasov, Vladislav Mikhailov, Vrinda Prabhu, Wilson Y. Lee, Wojciech Kusa, Xiangru Tang, Yacine Jernite, Yada Pruksachatkun, Yallow Uri, Yanis Labrak, Yash Shailesh Bajaj, Yash Venkatraman, Yifan Xu, Yingxin Xu, Yonatan Belinkov, Younes Belkada, Yoyo Yang, Yu Xu, Zachary Bamberger, Zach Nguyen, Zaid Alyafeai, Zden\\v{e}k Kasner, Zeerak Talat, Zheng-Xin Yong, Zhe Tan, Zhiqing Sun, Zhongli Xie, Zifan Ye","cross_cats":[],"headline":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model"},"references":{"count":249,"internal_anchors":25,"resolved_work":249,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Exploring BERT's Vocabulary , author =","work_id":"605ddbd8-95a1-46a3-acf7-9f76dbef11ba","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Proceedings of the AAAI conference on artificial intelligence , year =","work_id":"950f62ee-f6ad-4583-b7a3-a5f5abc211cd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"International Conference on Learning Representations , year=","work_id":"f7101c0a-5c39-4c12-b861-e59c16d6b22b","year":null},{"cited_arxiv_id":"","doi":"10.1145/3278721.3278729","is_internal_anchor":false,"ref_index":6,"title":"2018 , isbn =","work_id":"34eca032-d4af-4ba4-b657-d90a486e2c1b","year":2018},{"cited_arxiv_id":"","doi":"10.18653/v1/n18-2003","is_internal_anchor":false,"ref_index":7,"title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","work_id":"debd34b6-f412-41f5-8776-18ca1afb906a","year":2018}],"snapshot_sha256":"7e71e193cc11e2c0463df7ba363e2de37d26c3f44175f3f4a352a28d43d7a012"},"source":{"id":"2211.05100","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-12T00:38:59.003626Z","id":"1867d87f-ff1b-4e51-9042-b1abf1f16c2c","model_set":{"reader":"grok-4.3"},"one_line_summary":"BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A 176B-parameter decoder-only language model trained on text from 59 languages is built through open collaboration and released publicly.","strongest_claim":"BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning.","weakest_assumption":"That the unreported details of training procedure, data filtering, and benchmark evaluation setup produce generalizable capabilities rather than benchmark-specific artifacts."}},"verdict_id":"1867d87f-ff1b-4e51-9042-b1abf1f16c2c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d172a15354c6ba3dfcd3c447056fb42152760aba37bdf0262304f4df80f7819d","target":"record","created_at":"2026-07-05T06:24:47Z","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":"a91614a2148a6d8f971656f499d525ac14b911ee834764a20de434812533328d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T18:48:09Z","title_canon_sha256":"4e5fb9fbaefc58fa6703b8412964dfdb31658278632b938bb57a81956a15579a"},"schema_version":"1.0","source":{"id":"2211.05100","kind":"arxiv","version":4}},"canonical_sha256":"f88b41323660abaf12adf79189da6d48403d30888eb19042b14b57ac997206a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f88b41323660abaf12adf79189da6d48403d30888eb19042b14b57ac997206a2","first_computed_at":"2026-07-05T06:24:47.062628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:47.062628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ksq4nHjhUy1q++Q9i3jPj7Xm9t9R2jdC62/ZZODw3QtPu+Np3tlBuBeMgLLhPfEfPwoJzhTfvYGIp412M9B+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:47.063293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05100","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d172a15354c6ba3dfcd3c447056fb42152760aba37bdf0262304f4df80f7819d","sha256:22d04efc637257ceae80c032f549a1a08703bcc41d636b6aa1e0c29cc822f1bd"],"state_sha256":"1a00fe787ad7ab3ea0d3bfbf41b909fefcf6330af8ebed0f21c5194cdfd1713d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUgF91414CwZ5RdVxOImqI8dpxh0If0M8QQGVR1wz2D0ofJ7Dtbaj+gqQ51dr188CtAMa3BALhnQofkD8i21Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:38:32.105984Z","bundle_sha256":"f1e9439bae64d2e2b159ad249ddbf76957bfdfa102011b4db30e11b61eaeee3a"}}