{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IFSQEDY5JISYX6EXPNO6I363FR","short_pith_number":"pith:IFSQEDY5","canonical_record":{"source":{"id":"2409.17827","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T13:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"bb0ba2ce7154973c7e37fd03b35caaf0f91fadb30c36d071fb796e7335b9985a","abstract_canon_sha256":"ba28ce2faa750c4d40f2568e012224d5de427b25eea1b30f7040f34b69319a2f"},"schema_version":"1.0"},"canonical_sha256":"4165020f1d4a258bf8977b5de46fdb2c73bd55140640002e9679715f57ef4ec5","source":{"kind":"arxiv","id":"2409.17827","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17827","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17827v2","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17827","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"IFSQEDY5JISY","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"IFSQEDY5JISYX6EX","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"IFSQEDY5","created_at":"2026-07-05T09:12:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IFSQEDY5JISYX6EXPNO6I363FR","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17827","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T13:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"bb0ba2ce7154973c7e37fd03b35caaf0f91fadb30c36d071fb796e7335b9985a","abstract_canon_sha256":"ba28ce2faa750c4d40f2568e012224d5de427b25eea1b30f7040f34b69319a2f"},"schema_version":"1.0"},"canonical_sha256":"4165020f1d4a258bf8977b5de46fdb2c73bd55140640002e9679715f57ef4ec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:48.296446Z","signature_b64":"sPklGs4c421G0UhRaafRlwXQ2nAMC3WkzfwiIpA3fYT194NtEMoC4bX7D22Neqkhhlmk+A1KYnRLNrjzi42tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4165020f1d4a258bf8977b5de46fdb2c73bd55140640002e9679715f57ef4ec5","last_reissued_at":"2026-07-05T09:12:48.295928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:48.295928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17827","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":"2026-07-05T09:12:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e9D7a13/j2M3V/hCHLP9jJhlNzQ3SzDw+AwXSyCSFWcLS7WoEMVHC+w4qRFsx+FnX/3gVUzJMrrogNH/LSK+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:52:51.195140Z"},"content_sha256":"797418baf865397c95ed5da4e6e2efbf33f8c699e7c43e165558109f8b1a80ca","schema_version":"1.0","event_id":"sha256:797418baf865397c95ed5da4e6e2efbf33f8c699e7c43e165558109f8b1a80ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IFSQEDY5JISYX6EXPNO6I363FR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bradford Levy, Siyan Wang","submitted_at":"2024-09-26T13:26:46Z","abstract_excerpt":"Many of the recent breakthroughs in language modeling have resulted from scaling effectively the same model architecture to larger datasets. In this vein, recent work has highlighted performance gains from increasing training dataset size and quality, suggesting a need for novel sources of large-scale datasets. In this work, we introduce BeanCounter, a public dataset consisting of more than 159B tokens extracted from businesses' disclosures. We show that this data is indeed novel: less than 0.1% of BeanCounter appears in Common Crawl-based datasets and it is an order of magnitude larger than d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17827","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/2409.17827/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":"2026-07-05T09:12:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxxC7vBlGpnk3KgR2l485Rw5s/KcxRVqwXMcQq2O2D/INiqilHTjkTU4maKICEuZmy+pe1atzi5ZfTIRKwcTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:52:51.195628Z"},"content_sha256":"47970d3609d3e589abce2962007f6ae8358cb866b3a3270b14179eccee20fb10","schema_version":"1.0","event_id":"sha256:47970d3609d3e589abce2962007f6ae8358cb866b3a3270b14179eccee20fb10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFSQEDY5JISYX6EXPNO6I363FR/bundle.json","state_url":"https://pith.science/pith/IFSQEDY5JISYX6EXPNO6I363FR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFSQEDY5JISYX6EXPNO6I363FR/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":"2026-08-20T01:52:51Z","links":{"resolver":"https://pith.science/pith/IFSQEDY5JISYX6EXPNO6I363FR","bundle":"https://pith.science/pith/IFSQEDY5JISYX6EXPNO6I363FR/bundle.json","state":"https://pith.science/pith/IFSQEDY5JISYX6EXPNO6I363FR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFSQEDY5JISYX6EXPNO6I363FR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IFSQEDY5JISYX6EXPNO6I363FR","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":"ba28ce2faa750c4d40f2568e012224d5de427b25eea1b30f7040f34b69319a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T13:26:46Z","title_canon_sha256":"bb0ba2ce7154973c7e37fd03b35caaf0f91fadb30c36d071fb796e7335b9985a"},"schema_version":"1.0","source":{"id":"2409.17827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17827","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17827v2","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17827","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"IFSQEDY5JISY","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"IFSQEDY5JISYX6EX","created_at":"2026-07-05T09:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"IFSQEDY5","created_at":"2026-07-05T09:12:48Z"}],"graph_snapshots":[{"event_id":"sha256:47970d3609d3e589abce2962007f6ae8358cb866b3a3270b14179eccee20fb10","target":"graph","created_at":"2026-07-05T09:12:48Z","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/2409.17827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many of the recent breakthroughs in language modeling have resulted from scaling effectively the same model architecture to larger datasets. In this vein, recent work has highlighted performance gains from increasing training dataset size and quality, suggesting a need for novel sources of large-scale datasets. In this work, we introduce BeanCounter, a public dataset consisting of more than 159B tokens extracted from businesses' disclosures. We show that this data is indeed novel: less than 0.1% of BeanCounter appears in Common Crawl-based datasets and it is an order of magnitude larger than d","authors_text":"Bradford Levy, Siyan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T13:26:46Z","title":"BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17827","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":"sha256:797418baf865397c95ed5da4e6e2efbf33f8c699e7c43e165558109f8b1a80ca","target":"record","created_at":"2026-07-05T09:12:48Z","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":"ba28ce2faa750c4d40f2568e012224d5de427b25eea1b30f7040f34b69319a2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T13:26:46Z","title_canon_sha256":"bb0ba2ce7154973c7e37fd03b35caaf0f91fadb30c36d071fb796e7335b9985a"},"schema_version":"1.0","source":{"id":"2409.17827","kind":"arxiv","version":2}},"canonical_sha256":"4165020f1d4a258bf8977b5de46fdb2c73bd55140640002e9679715f57ef4ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4165020f1d4a258bf8977b5de46fdb2c73bd55140640002e9679715f57ef4ec5","first_computed_at":"2026-07-05T09:12:48.295928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:48.295928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sPklGs4c421G0UhRaafRlwXQ2nAMC3WkzfwiIpA3fYT194NtEMoC4bX7D22Neqkhhlmk+A1KYnRLNrjzi42tCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:48.296446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:797418baf865397c95ed5da4e6e2efbf33f8c699e7c43e165558109f8b1a80ca","sha256:47970d3609d3e589abce2962007f6ae8358cb866b3a3270b14179eccee20fb10"],"state_sha256":"e1a38d428645a4bc556fb260ab0ee73980c792320ae1652f8cf8f7c85373c0a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gc4VF5+PBHRg7JvymMTQRlz9UiuN55wXWdH07GzP5vwUDpSegL5N5Hnem3Cx19c/1Mo+9RPBDWsMhYoLWKi4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:52:51.199816Z","bundle_sha256":"2b1ba6eb6b53acee6ee35b5396ff3aabb3f1f20510090215736f5a894b74d6d6"}}