{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OYBOQ7DW5U26WM52NHVE3XJ53K","short_pith_number":"pith:OYBOQ7DW","schema_version":"1.0","canonical_sha256":"7602e87c76ed35eb33ba69ea4ddd3ddab60763dbf58768ba2bbb4e568473f5df","source":{"kind":"arxiv","id":"2307.16562","version":1},"attestation_state":"computed","paper":{"title":"SAKSHI: Decentralized AI Platforms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Ashwin Hebbar, Canhui Chen, Himanshu Tyagi, Peiyao Sheng, Pramod Viswanath, Ranvir Rana, Sreeram Kannan, Suma Bhat, Xuechao Wang, Zerui Cheng, Zhixuan Fang","submitted_at":"2023-07-31T10:48:56Z","abstract_excerpt":"Large AI models (e.g., Dall-E, GPT4) have electrified the scientific, technological and societal landscape through their superhuman capabilities. These services are offered largely in a traditional web2.0 format (e.g., OpenAI's GPT4 service). As more large AI models proliferate (personalizing and specializing to a variety of domains), there is a tremendous need to have a neutral trust-free platform that allows the hosting of AI models, clients receiving AI services efficiently, yet in a trust-free, incentive compatible, Byzantine behavior resistant manner. In this paper we propose SAKSHI, a tr"},"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":"2307.16562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2023-07-31T10:48:56Z","cross_cats_sorted":[],"title_canon_sha256":"9b2f0e6facf6044d6565ab9af41963cbac06f5e596e74d8c97a12220d3dcadfd","abstract_canon_sha256":"b463ec621484d20fbd88d533e48c8b9bc22c80a6d0a70e2bbd1872449adc0b9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:05.271876Z","signature_b64":"7SoiC9W6XRawJ4BGdKxf4mxTJrc/OAFBPD6K0ofiRIe5M6Uc9Uj0k5Vl4WHGxiQuR/kbIPyco+JXY/SuY96hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7602e87c76ed35eb33ba69ea4ddd3ddab60763dbf58768ba2bbb4e568473f5df","last_reissued_at":"2026-07-05T06:36:05.271420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:05.271420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAKSHI: Decentralized AI Platforms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Ashwin Hebbar, Canhui Chen, Himanshu Tyagi, Peiyao Sheng, Pramod Viswanath, Ranvir Rana, Sreeram Kannan, Suma Bhat, Xuechao Wang, Zerui Cheng, Zhixuan Fang","submitted_at":"2023-07-31T10:48:56Z","abstract_excerpt":"Large AI models (e.g., Dall-E, GPT4) have electrified the scientific, technological and societal landscape through their superhuman capabilities. These services are offered largely in a traditional web2.0 format (e.g., OpenAI's GPT4 service). As more large AI models proliferate (personalizing and specializing to a variety of domains), there is a tremendous need to have a neutral trust-free platform that allows the hosting of AI models, clients receiving AI services efficiently, yet in a trust-free, incentive compatible, Byzantine behavior resistant manner. In this paper we propose SAKSHI, a tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16562","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/2307.16562/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":"2307.16562","created_at":"2026-07-05T06:36:05.271472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16562v1","created_at":"2026-07-05T06:36:05.271472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16562","created_at":"2026-07-05T06:36:05.271472+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYBOQ7DW5U26","created_at":"2026-07-05T06:36:05.271472+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYBOQ7DW5U26WM52","created_at":"2026-07-05T06:36:05.271472+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYBOQ7DW","created_at":"2026-07-05T06:36:05.271472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04810","citing_title":"Game of Coding for Vector-Valued Computations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07841","citing_title":"\\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K","json":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K.json","graph_json":"https://pith.science/api/pith-number/OYBOQ7DW5U26WM52NHVE3XJ53K/graph.json","events_json":"https://pith.science/api/pith-number/OYBOQ7DW5U26WM52NHVE3XJ53K/events.json","paper":"https://pith.science/paper/OYBOQ7DW"},"agent_actions":{"view_html":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K","download_json":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K.json","view_paper":"https://pith.science/paper/OYBOQ7DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16562&json=true","fetch_graph":"https://pith.science/api/pith-number/OYBOQ7DW5U26WM52NHVE3XJ53K/graph.json","fetch_events":"https://pith.science/api/pith-number/OYBOQ7DW5U26WM52NHVE3XJ53K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K/action/storage_attestation","attest_author":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K/action/author_attestation","sign_citation":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K/action/citation_signature","submit_replication":"https://pith.science/pith/OYBOQ7DW5U26WM52NHVE3XJ53K/action/replication_record"}},"created_at":"2026-07-05T06:36:05.271472+00:00","updated_at":"2026-07-05T06:36:05.271472+00:00"}