{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AB4F7UXCIIEH6NQZUWQ5NOGM6J","short_pith_number":"pith:AB4F7UXC","canonical_record":{"source":{"id":"2407.09241","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T13:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"f80c0d907b96fd0f6cb44a18cdfcffababe7a73d8d1651504dbf1d014d7cc1d6","abstract_canon_sha256":"54c7b120c5fe2048a60964844d2692477d6b0f1ed0f07847dfd486b655fe8711"},"schema_version":"1.0"},"canonical_sha256":"00785fd2e242087f3619a5a1d6b8ccf268ecd1618b43c55c936902f03a0b165b","source":{"kind":"arxiv","id":"2407.09241","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09241","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09241v1","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09241","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_12","alias_value":"AB4F7UXCIIEH","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_16","alias_value":"AB4F7UXCIIEH6NQZ","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_8","alias_value":"AB4F7UXC","created_at":"2026-07-05T08:43:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AB4F7UXCIIEH6NQZUWQ5NOGM6J","target":"record","payload":{"canonical_record":{"source":{"id":"2407.09241","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T13:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"f80c0d907b96fd0f6cb44a18cdfcffababe7a73d8d1651504dbf1d014d7cc1d6","abstract_canon_sha256":"54c7b120c5fe2048a60964844d2692477d6b0f1ed0f07847dfd486b655fe8711"},"schema_version":"1.0"},"canonical_sha256":"00785fd2e242087f3619a5a1d6b8ccf268ecd1618b43c55c936902f03a0b165b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:16.878452Z","signature_b64":"9sWxCGqn3BpUPeiAHFz11OYHnS9O6Q5LwZKtMiTAi11eKRCQ719jB3bjuqXS70M6zRf5Qqznm74s0hjD1Su3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00785fd2e242087f3619a5a1d6b8ccf268ecd1618b43c55c936902f03a0b165b","last_reissued_at":"2026-07-05T08:43:16.878077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:16.878077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.09241","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sMBjK5wGd+PhN37tq+wermbDazJ2nm2cTHJTUxH+odn4MlxniSLKQ6IMBxj7w9LFiIUtWyQ6RqLrSrt7StauBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:16:10.298312Z"},"content_sha256":"216956a847c94976d33e07dd4191b8668c8829a9b667bfc705968b778b196b7a","schema_version":"1.0","event_id":"sha256:216956a847c94976d33e07dd4191b8668c8829a9b667bfc705968b778b196b7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AB4F7UXCIIEH6NQZUWQ5NOGM6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Sociolinguistic Foundations of Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akira Murakami, Alejandro Jawerbaum, Bodo Winter, Dana Roemling, Jack Grieve, Jason Grafmiller, Marcus Perlman, Matteo Fuoli, Sara Bartl, Weihang Huang","submitted_at":"2024-07-12T13:12:55Z","abstract_excerpt":"In this paper, we introduce a sociolinguistic perspective on language modeling. We claim that large language models are inherently models of varieties of language, and we consider how this insight can inform the development and deployment of large language models. We begin by presenting a technical definition of the concept of a variety of language as developed in sociolinguistics. We then discuss how this perspective can help address five basic challenges in language modeling: social bias, domain adaptation, alignment, language change, and scale. Ultimately, we argue that it is crucial to car"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09241","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/2407.09241/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":"2026-07-05T08:43:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WF5IBgpzvKsRMyYbQZKxkjhgjd3kpoS7VIQUiBachivDLRB7QRHRApJddCcNGeFnTlBxWFWEyO7LoRGKbtg9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:16:10.298907Z"},"content_sha256":"527babac165ce5fb0dbb3b7a81448c097d563360eae9b2dacfdacc27b08e475b","schema_version":"1.0","event_id":"sha256:527babac165ce5fb0dbb3b7a81448c097d563360eae9b2dacfdacc27b08e475b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/bundle.json","state_url":"https://pith.science/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/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":"2026-08-03T16:16:10Z","links":{"resolver":"https://pith.science/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J","bundle":"https://pith.science/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/bundle.json","state":"https://pith.science/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AB4F7UXCIIEH6NQZUWQ5NOGM6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AB4F7UXCIIEH6NQZUWQ5NOGM6J","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":"54c7b120c5fe2048a60964844d2692477d6b0f1ed0f07847dfd486b655fe8711","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T13:12:55Z","title_canon_sha256":"f80c0d907b96fd0f6cb44a18cdfcffababe7a73d8d1651504dbf1d014d7cc1d6"},"schema_version":"1.0","source":{"id":"2407.09241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09241","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09241v1","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09241","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_12","alias_value":"AB4F7UXCIIEH","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_16","alias_value":"AB4F7UXCIIEH6NQZ","created_at":"2026-07-05T08:43:16Z"},{"alias_kind":"pith_short_8","alias_value":"AB4F7UXC","created_at":"2026-07-05T08:43:16Z"}],"graph_snapshots":[{"event_id":"sha256:527babac165ce5fb0dbb3b7a81448c097d563360eae9b2dacfdacc27b08e475b","target":"graph","created_at":"2026-07-05T08:43:16Z","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/2407.09241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a sociolinguistic perspective on language modeling. We claim that large language models are inherently models of varieties of language, and we consider how this insight can inform the development and deployment of large language models. We begin by presenting a technical definition of the concept of a variety of language as developed in sociolinguistics. We then discuss how this perspective can help address five basic challenges in language modeling: social bias, domain adaptation, alignment, language change, and scale. Ultimately, we argue that it is crucial to car","authors_text":"Akira Murakami, Alejandro Jawerbaum, Bodo Winter, Dana Roemling, Jack Grieve, Jason Grafmiller, Marcus Perlman, Matteo Fuoli, Sara Bartl, Weihang Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T13:12:55Z","title":"The Sociolinguistic Foundations of Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09241","kind":"arxiv","version":1},"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":"sha256:216956a847c94976d33e07dd4191b8668c8829a9b667bfc705968b778b196b7a","target":"record","created_at":"2026-07-05T08:43:16Z","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":"54c7b120c5fe2048a60964844d2692477d6b0f1ed0f07847dfd486b655fe8711","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T13:12:55Z","title_canon_sha256":"f80c0d907b96fd0f6cb44a18cdfcffababe7a73d8d1651504dbf1d014d7cc1d6"},"schema_version":"1.0","source":{"id":"2407.09241","kind":"arxiv","version":1}},"canonical_sha256":"00785fd2e242087f3619a5a1d6b8ccf268ecd1618b43c55c936902f03a0b165b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00785fd2e242087f3619a5a1d6b8ccf268ecd1618b43c55c936902f03a0b165b","first_computed_at":"2026-07-05T08:43:16.878077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:16.878077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9sWxCGqn3BpUPeiAHFz11OYHnS9O6Q5LwZKtMiTAi11eKRCQ719jB3bjuqXS70M6zRf5Qqznm74s0hjD1Su3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:16.878452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:216956a847c94976d33e07dd4191b8668c8829a9b667bfc705968b778b196b7a","sha256:527babac165ce5fb0dbb3b7a81448c097d563360eae9b2dacfdacc27b08e475b"],"state_sha256":"d8accfbd50efde9aecc762059bedc4d14e99567a7edc2d4a45cdd1b9b3228441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9HuVtHw97qJMthtGx7vlnZogGR+IaDN3HnkgDJtQSvC7uiuk+5iZKf+WtCZqTuu7AnPa4xxjMhEoU5eApOHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:16:10.303423Z","bundle_sha256":"b7813400b0698cacb525801c2ac1d9a9fca095b4f05cf71175628933b3324620"}}