{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JX362SJZIUBIIDTLCZ4EATFGFY","short_pith_number":"pith:JX362SJZ","canonical_record":{"source":{"id":"2301.03988","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-09T10:52:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5977d6b3f26451d15f26a7eeb368858d1627f8e44a91d61f0ef65d81aed92219","abstract_canon_sha256":"aa54b56b0c62444ade79c20028186292b033255e91871d30762dce123978bd14"},"schema_version":"1.0"},"canonical_sha256":"4df7ed49394502840e6b1678404ca62e38be9fd0a631c490b8d63f6a1ed0ac7c","source":{"kind":"arxiv","id":"2301.03988","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.03988","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"arxiv_version","alias_value":"2301.03988v2","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03988","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_12","alias_value":"JX362SJZIUBI","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_16","alias_value":"JX362SJZIUBIIDTL","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_8","alias_value":"JX362SJZ","created_at":"2026-07-05T05:45:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JX362SJZIUBIIDTLCZ4EATFGFY","target":"record","payload":{"canonical_record":{"source":{"id":"2301.03988","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-09T10:52:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5977d6b3f26451d15f26a7eeb368858d1627f8e44a91d61f0ef65d81aed92219","abstract_canon_sha256":"aa54b56b0c62444ade79c20028186292b033255e91871d30762dce123978bd14"},"schema_version":"1.0"},"canonical_sha256":"4df7ed49394502840e6b1678404ca62e38be9fd0a631c490b8d63f6a1ed0ac7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:06.370782Z","signature_b64":"y29ILZemylgSDqrmFmhosF/lnvEvhXQxqidpIyv72OF0T2BzNQnTZlYXQ/gIuszzHw0XLpc9f9hOE6gmES0pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df7ed49394502840e6b1678404ca62e38be9fd0a631c490b8d63f6a1ed0ac7c","last_reissued_at":"2026-07-05T05:45:06.370261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:06.370261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.03988","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:45:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLMUwlXcB2ji7V68IrIPngtdPN9aGrdzmCgIfTuO6Ef7L+xFGBxjlM7DrIln6/Uz4o8JWFN24JcNAQG9NZtsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:16.900279Z"},"content_sha256":"0737adca8186c60d70217f3ba32c7d829feeadb32f1b421740274569b7c99dc5","schema_version":"1.0","event_id":"sha256:0737adca8186c60d70217f3ba32c7d829feeadb32f1b421740274569b7c99dc5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JX362SJZIUBIIDTLCZ4EATFGFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SantaCoder: don't reach for the stars!","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Alex Gu, Arjun Guha, Bernardo Garc\\'ia del R\\'io, Carlos Munoz Ferrandis, Carolyn Jane Anderson, Chenghao Mou, Christopher Akiki, Daniel Fried, Danish Contractor, David Lansky, Denis Kocetkov, Dmitry Abulkhanov, Dzmitry Bahdanau, Francesco De Toni, Hailey Schoelkopf, Harm de Vries, Huu Nguyen, Ian Yu, Jia Li, Joel Lamy Poirier, Leandro Von Werra, Logesh Kumar Umapathi, Loubna Ben Allal, Luis Villa, Manan Dey, Manuel Romero, Marco Zocca, Mayank Mishra, Michael Lappert, Niklas Muennighoff, Paulo Villegas, Qian Liu, Raymond Li, Sean Hughes, Sergey Troshin, Shamik Bose, Sourab Mangrulkar, Terry Yue Zhuo, Urvashi Bhattacharyya, Yacine Jernite, Yangtian Zi","submitted_at":"2023-01-09T10:52:35Z","abstract_excerpt":"The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code. This tech report describes the progress of the collaboration until December 2022, outlining the current state of the Personally Identifiable Information (PII) redaction pipeline, the experiments conducted to de-risk the model architecture, and the experiments investigating better preprocessing methods for the training data. We train 1.1B parameter models on the Java, JavaScript, and Python subsets of The Stack and evaluate them on the MultiPL-E text-to-code benchmar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03988","kind":"arxiv","version":2},"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/2301.03988/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":"2026-07-05T05:45:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KlWqdCbjDxIuIN7RYxSzPWeRTslTPuR3wxafOCfSZNyuwdNYAZWxq+5HGYLDgKbn9KiXEe0xDdUVrehZz/LOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:16.900694Z"},"content_sha256":"d0b2b3a967f17c758aa1114aa02e0f761de38fe7b6ee6dca2d0d753d8fcdb434","schema_version":"1.0","event_id":"sha256:d0b2b3a967f17c758aa1114aa02e0f761de38fe7b6ee6dca2d0d753d8fcdb434"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JX362SJZIUBIIDTLCZ4EATFGFY/bundle.json","state_url":"https://pith.science/pith/JX362SJZIUBIIDTLCZ4EATFGFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JX362SJZIUBIIDTLCZ4EATFGFY/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":"2026-07-07T06:39:16Z","links":{"resolver":"https://pith.science/pith/JX362SJZIUBIIDTLCZ4EATFGFY","bundle":"https://pith.science/pith/JX362SJZIUBIIDTLCZ4EATFGFY/bundle.json","state":"https://pith.science/pith/JX362SJZIUBIIDTLCZ4EATFGFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JX362SJZIUBIIDTLCZ4EATFGFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JX362SJZIUBIIDTLCZ4EATFGFY","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":"aa54b56b0c62444ade79c20028186292b033255e91871d30762dce123978bd14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-09T10:52:35Z","title_canon_sha256":"5977d6b3f26451d15f26a7eeb368858d1627f8e44a91d61f0ef65d81aed92219"},"schema_version":"1.0","source":{"id":"2301.03988","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.03988","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"arxiv_version","alias_value":"2301.03988v2","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03988","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_12","alias_value":"JX362SJZIUBI","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_16","alias_value":"JX362SJZIUBIIDTL","created_at":"2026-07-05T05:45:06Z"},{"alias_kind":"pith_short_8","alias_value":"JX362SJZ","created_at":"2026-07-05T05:45:06Z"}],"graph_snapshots":[{"event_id":"sha256:d0b2b3a967f17c758aa1114aa02e0f761de38fe7b6ee6dca2d0d753d8fcdb434","target":"graph","created_at":"2026-07-05T05:45:06Z","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/2301.03988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code. This tech report describes the progress of the collaboration until December 2022, outlining the current state of the Personally Identifiable Information (PII) redaction pipeline, the experiments conducted to de-risk the model architecture, and the experiments investigating better preprocessing methods for the training data. We train 1.1B parameter models on the Java, JavaScript, and Python subsets of The Stack and evaluate them on the MultiPL-E text-to-code benchmar","authors_text":"Alex Gu, Arjun Guha, Bernardo Garc\\'ia del R\\'io, Carlos Munoz Ferrandis, Carolyn Jane Anderson, Chenghao Mou, Christopher Akiki, Daniel Fried, Danish Contractor, David Lansky, Denis Kocetkov, Dmitry Abulkhanov, Dzmitry Bahdanau, Francesco De Toni, Hailey Schoelkopf, Harm de Vries, Huu Nguyen, Ian Yu, Jia Li, Joel Lamy Poirier, Leandro Von Werra, Logesh Kumar Umapathi, Loubna Ben Allal, Luis Villa, Manan Dey, Manuel Romero, Marco Zocca, Mayank Mishra, Michael Lappert, Niklas Muennighoff, Paulo Villegas, Qian Liu, Raymond Li, Sean Hughes, Sergey Troshin, Shamik Bose, Sourab Mangrulkar, Terry Yue Zhuo, Urvashi Bhattacharyya, Yacine Jernite, Yangtian Zi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-09T10:52:35Z","title":"SantaCoder: don't reach for the stars!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03988","kind":"arxiv","version":2},"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":"sha256:0737adca8186c60d70217f3ba32c7d829feeadb32f1b421740274569b7c99dc5","target":"record","created_at":"2026-07-05T05:45:06Z","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":"aa54b56b0c62444ade79c20028186292b033255e91871d30762dce123978bd14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-09T10:52:35Z","title_canon_sha256":"5977d6b3f26451d15f26a7eeb368858d1627f8e44a91d61f0ef65d81aed92219"},"schema_version":"1.0","source":{"id":"2301.03988","kind":"arxiv","version":2}},"canonical_sha256":"4df7ed49394502840e6b1678404ca62e38be9fd0a631c490b8d63f6a1ed0ac7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4df7ed49394502840e6b1678404ca62e38be9fd0a631c490b8d63f6a1ed0ac7c","first_computed_at":"2026-07-05T05:45:06.370261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:06.370261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y29ILZemylgSDqrmFmhosF/lnvEvhXQxqidpIyv72OF0T2BzNQnTZlYXQ/gIuszzHw0XLpc9f9hOE6gmES0pBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:06.370782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.03988","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0737adca8186c60d70217f3ba32c7d829feeadb32f1b421740274569b7c99dc5","sha256:d0b2b3a967f17c758aa1114aa02e0f761de38fe7b6ee6dca2d0d753d8fcdb434"],"state_sha256":"ff99305ffe5efe186bf76c8d26ffea901be257c0c679a84138570f9e148afc2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPdJyP2LVPS8BMGF+2t6lIndbn+IIyE6gWmfphcqeLHbeChBRpOxsVRAag7/jNXsgQIQ9x4clRi6Vlrsx7wZCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:39:16.906627Z","bundle_sha256":"8589cf0795161cd5c317170ca5947c13f4e72b7805fedff19193d3d453bae6ae"}}