{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YBEYGQAN4ZR65VYC6VA6TGQV4P","short_pith_number":"pith:YBEYGQAN","canonical_record":{"source":{"id":"2410.22587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T23:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"d75fe3a00e07ed6a9c025d276bb02ea38abb3378d2afd12af6f71a6b750dfe2b","abstract_canon_sha256":"6e6a12ab7f24a89151aada3b17b62b5468a4ea8e6e2bc5cd3aa2ce5d574adc5e"},"schema_version":"1.0"},"canonical_sha256":"c04983400de663eed702f541e99a15e3fc1c9fa7a9db931c094d26cb71388892","source":{"kind":"arxiv","id":"2410.22587","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22587","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22587v2","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22587","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"YBEYGQAN4ZR6","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"YBEYGQAN4ZR65VYC","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"YBEYGQAN","created_at":"2026-07-05T09:36:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YBEYGQAN4ZR65VYC6VA6TGQV4P","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T23:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"d75fe3a00e07ed6a9c025d276bb02ea38abb3378d2afd12af6f71a6b750dfe2b","abstract_canon_sha256":"6e6a12ab7f24a89151aada3b17b62b5468a4ea8e6e2bc5cd3aa2ce5d574adc5e"},"schema_version":"1.0"},"canonical_sha256":"c04983400de663eed702f541e99a15e3fc1c9fa7a9db931c094d26cb71388892","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:49.329973Z","signature_b64":"eyAnDEcxWCagzquwYwtlPwt7nYCmumea9nET419tbQxeH/lLwFClWCikZA1p+35eTmb0sDJwNPZRONiSUyL+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04983400de663eed702f541e99a15e3fc1c9fa7a9db931c094d26cb71388892","last_reissued_at":"2026-07-05T09:36:49.329384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:49.329384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22587","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":"2026-07-05T09:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OlGtlI8QqnqxtsYOSiRkQzJTi/z7O6FXIP6Je0dvutJMQjnhmAm7F8HXxTJMHQpR5dKEeQRPQIiX2/HlWFnCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:39:04.186551Z"},"content_sha256":"144b79a9c1a0db887e9a043367eb3f45f37f140963e01df5fcef077d8ffed458","schema_version":"1.0","event_id":"sha256:144b79a9c1a0db887e9a043367eb3f45f37f140963e01df5fcef077d8ffed458"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YBEYGQAN4ZR65VYC6VA6TGQV4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Arnett, Eliot Jones, Ivan P. Yamshchikov, Pierre-Carl Langlais","submitted_at":"2024-10-29T23:00:05Z","abstract_excerpt":"Open-source large language models are becoming increasingly available and popular among researchers and practitioners. While significant progress has been made on open-weight models, open training data is a practice yet to be adopted by the leading open-weight models creators. At the same time, there researchers are working to make language models safer. We propose a data curation pipeline to reduce harmful outputs by models trained on public domain data. There are unique challenges to working with public domain data, as these sources differ from web text in both form and content. Many sources"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22587","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/2410.22587/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":"2026-07-05T09:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+737MouRiorNfOWhuRusOmGZ9ChWblCUTsuU5nKX0FDJRP2sL4MACUoqLW9wUJvUn41o4bgH21E+xV+UvAkQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:39:04.187054Z"},"content_sha256":"b94c3c3406f2242f9800655c70d52061e3e29f29fc45e3deb276c70cca07b3fd","schema_version":"1.0","event_id":"sha256:b94c3c3406f2242f9800655c70d52061e3e29f29fc45e3deb276c70cca07b3fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/bundle.json","state_url":"https://pith.science/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/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":"2026-08-16T19:39:04Z","links":{"resolver":"https://pith.science/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P","bundle":"https://pith.science/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/bundle.json","state":"https://pith.science/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBEYGQAN4ZR65VYC6VA6TGQV4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YBEYGQAN4ZR65VYC6VA6TGQV4P","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":"6e6a12ab7f24a89151aada3b17b62b5468a4ea8e6e2bc5cd3aa2ce5d574adc5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T23:00:05Z","title_canon_sha256":"d75fe3a00e07ed6a9c025d276bb02ea38abb3378d2afd12af6f71a6b750dfe2b"},"schema_version":"1.0","source":{"id":"2410.22587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22587","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22587v2","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22587","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"YBEYGQAN4ZR6","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"YBEYGQAN4ZR65VYC","created_at":"2026-07-05T09:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"YBEYGQAN","created_at":"2026-07-05T09:36:49Z"}],"graph_snapshots":[{"event_id":"sha256:b94c3c3406f2242f9800655c70d52061e3e29f29fc45e3deb276c70cca07b3fd","target":"graph","created_at":"2026-07-05T09:36:49Z","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/2410.22587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-source large language models are becoming increasingly available and popular among researchers and practitioners. While significant progress has been made on open-weight models, open training data is a practice yet to be adopted by the leading open-weight models creators. At the same time, there researchers are working to make language models safer. We propose a data curation pipeline to reduce harmful outputs by models trained on public domain data. There are unique challenges to working with public domain data, as these sources differ from web text in both form and content. Many sources","authors_text":"Catherine Arnett, Eliot Jones, Ivan P. Yamshchikov, Pierre-Carl Langlais","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T23:00:05Z","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22587","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":"sha256:144b79a9c1a0db887e9a043367eb3f45f37f140963e01df5fcef077d8ffed458","target":"record","created_at":"2026-07-05T09:36:49Z","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":"6e6a12ab7f24a89151aada3b17b62b5468a4ea8e6e2bc5cd3aa2ce5d574adc5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T23:00:05Z","title_canon_sha256":"d75fe3a00e07ed6a9c025d276bb02ea38abb3378d2afd12af6f71a6b750dfe2b"},"schema_version":"1.0","source":{"id":"2410.22587","kind":"arxiv","version":2}},"canonical_sha256":"c04983400de663eed702f541e99a15e3fc1c9fa7a9db931c094d26cb71388892","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c04983400de663eed702f541e99a15e3fc1c9fa7a9db931c094d26cb71388892","first_computed_at":"2026-07-05T09:36:49.329384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:49.329384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyAnDEcxWCagzquwYwtlPwt7nYCmumea9nET419tbQxeH/lLwFClWCikZA1p+35eTmb0sDJwNPZRONiSUyL+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:49.329973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:144b79a9c1a0db887e9a043367eb3f45f37f140963e01df5fcef077d8ffed458","sha256:b94c3c3406f2242f9800655c70d52061e3e29f29fc45e3deb276c70cca07b3fd"],"state_sha256":"90ae9885207dae62185b3ec1f02d9289e9765fc0a2ffb10334e35743e414a5c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mo4gBGlSlTLWZ8k8GlfAMlla3Oi3bgdKNiU0MZt3pIMfNeANuyAbmCTsyiIev3iplh6mzlsg5H8XfwPNuNZfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:39:04.191374Z","bundle_sha256":"0b72a2a59369453215d35eba8d2c9fc155b423deab178b2e8506f38cbfb2f3e6"}}