{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OBZUEMUFDTUV64SVIOFDJATQLL","short_pith_number":"pith:OBZUEMUF","canonical_record":{"source":{"id":"2404.14994","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T12:51:37Z","cross_cats_sorted":["cs.AI","cs.CC","cs.FL","cs.LG"],"title_canon_sha256":"c95c9f01898a41774cbbab6ef167227fa41b2c94f3c051bf32ef2924dc7175be","abstract_canon_sha256":"adbc72b2f143d1a359fde0de46ac66e34f6a0382c37ab1380722fe580daae5d5"},"schema_version":"1.0"},"canonical_sha256":"70734232851ce95f7255438a3482705ac7da3cc7e41d40b332dc2436e740a72f","source":{"kind":"arxiv","id":"2404.14994","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14994","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14994v3","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14994","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"OBZUEMUFDTUV","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"OBZUEMUFDTUV64SV","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"OBZUEMUF","created_at":"2026-07-05T08:34:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OBZUEMUFDTUV64SVIOFDJATQLL","target":"record","payload":{"canonical_record":{"source":{"id":"2404.14994","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T12:51:37Z","cross_cats_sorted":["cs.AI","cs.CC","cs.FL","cs.LG"],"title_canon_sha256":"c95c9f01898a41774cbbab6ef167227fa41b2c94f3c051bf32ef2924dc7175be","abstract_canon_sha256":"adbc72b2f143d1a359fde0de46ac66e34f6a0382c37ab1380722fe580daae5d5"},"schema_version":"1.0"},"canonical_sha256":"70734232851ce95f7255438a3482705ac7da3cc7e41d40b332dc2436e740a72f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:47.789475Z","signature_b64":"s1tN4T4BU7vP+RuaM4GX6+LGXlacgxS8t1Y0M8W3DCxd49aXZBEPntOumgQMXh+C0xkma1/Bsr4Y9VVj93AxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70734232851ce95f7255438a3482705ac7da3cc7e41d40b332dc2436e740a72f","last_reissued_at":"2026-07-05T08:34:47.788962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:47.788962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.14994","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PKSrUEUt1l3eOrugPH76z90czjHG7AiisqvqqKSgbeiA5k1tlWXunK1QyvnADLJam2EtVnoj/JuK84+p/S1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T04:48:45.325329Z"},"content_sha256":"fdff029415fc8ecdf94ae0ac34005ec490f264df7bcb201091af605bffd0d7c9","schema_version":"1.0","event_id":"sha256:fdff029415fc8ecdf94ae0ac34005ec490f264df7bcb201091af605bffd0d7c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OBZUEMUFDTUV64SVIOFDJATQLL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers Can Represent $n$-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.FL","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anej Svete, Ryan Cotterell","submitted_at":"2024-04-23T12:51:37Z","abstract_excerpt":"Existing work has analyzed the representational capacity of the transformer architecture by means of formal models of computation. However, the focus so far has been on analyzing the architecture in terms of language \\emph{acceptance}. We contend that this is an ill-suited problem in the study of \\emph{language models} (LMs), which are definitionally \\emph{probability distributions} over strings. In this paper, we focus on the relationship between transformer LMs and $n$-gram LMs, a simple and historically relevant class of language models. We show that transformer LMs using the hard or sparse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14994","kind":"arxiv","version":3},"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/2404.14994/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":"2026-07-05T08:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3uWxe7Ucj/j9hXis/hsNJVUU8EdSskrEgifJ1B7VAEB1RGxGWWlAI52QPfRHi8AgHgAsOsQ8eL5rqLQnHPRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T04:48:45.325832Z"},"content_sha256":"f99c03da7eb2a13110e333876f3c7a4e6fa8455a6625369998dd07f63a593377","schema_version":"1.0","event_id":"sha256:f99c03da7eb2a13110e333876f3c7a4e6fa8455a6625369998dd07f63a593377"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBZUEMUFDTUV64SVIOFDJATQLL/bundle.json","state_url":"https://pith.science/pith/OBZUEMUFDTUV64SVIOFDJATQLL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBZUEMUFDTUV64SVIOFDJATQLL/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":"2026-08-03T04:48:45Z","links":{"resolver":"https://pith.science/pith/OBZUEMUFDTUV64SVIOFDJATQLL","bundle":"https://pith.science/pith/OBZUEMUFDTUV64SVIOFDJATQLL/bundle.json","state":"https://pith.science/pith/OBZUEMUFDTUV64SVIOFDJATQLL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBZUEMUFDTUV64SVIOFDJATQLL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OBZUEMUFDTUV64SVIOFDJATQLL","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":"adbc72b2f143d1a359fde0de46ac66e34f6a0382c37ab1380722fe580daae5d5","cross_cats_sorted":["cs.AI","cs.CC","cs.FL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T12:51:37Z","title_canon_sha256":"c95c9f01898a41774cbbab6ef167227fa41b2c94f3c051bf32ef2924dc7175be"},"schema_version":"1.0","source":{"id":"2404.14994","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14994","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14994v3","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14994","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"OBZUEMUFDTUV","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"OBZUEMUFDTUV64SV","created_at":"2026-07-05T08:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"OBZUEMUF","created_at":"2026-07-05T08:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:f99c03da7eb2a13110e333876f3c7a4e6fa8455a6625369998dd07f63a593377","target":"graph","created_at":"2026-07-05T08:34:47Z","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/2404.14994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing work has analyzed the representational capacity of the transformer architecture by means of formal models of computation. However, the focus so far has been on analyzing the architecture in terms of language \\emph{acceptance}. We contend that this is an ill-suited problem in the study of \\emph{language models} (LMs), which are definitionally \\emph{probability distributions} over strings. In this paper, we focus on the relationship between transformer LMs and $n$-gram LMs, a simple and historically relevant class of language models. We show that transformer LMs using the hard or sparse","authors_text":"Anej Svete, Ryan Cotterell","cross_cats":["cs.AI","cs.CC","cs.FL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T12:51:37Z","title":"Transformers Can Represent $n$-gram Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14994","kind":"arxiv","version":3},"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:fdff029415fc8ecdf94ae0ac34005ec490f264df7bcb201091af605bffd0d7c9","target":"record","created_at":"2026-07-05T08:34:47Z","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":"adbc72b2f143d1a359fde0de46ac66e34f6a0382c37ab1380722fe580daae5d5","cross_cats_sorted":["cs.AI","cs.CC","cs.FL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T12:51:37Z","title_canon_sha256":"c95c9f01898a41774cbbab6ef167227fa41b2c94f3c051bf32ef2924dc7175be"},"schema_version":"1.0","source":{"id":"2404.14994","kind":"arxiv","version":3}},"canonical_sha256":"70734232851ce95f7255438a3482705ac7da3cc7e41d40b332dc2436e740a72f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70734232851ce95f7255438a3482705ac7da3cc7e41d40b332dc2436e740a72f","first_computed_at":"2026-07-05T08:34:47.788962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:47.788962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s1tN4T4BU7vP+RuaM4GX6+LGXlacgxS8t1Y0M8W3DCxd49aXZBEPntOumgQMXh+C0xkma1/Bsr4Y9VVj93AxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:47.789475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14994","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdff029415fc8ecdf94ae0ac34005ec490f264df7bcb201091af605bffd0d7c9","sha256:f99c03da7eb2a13110e333876f3c7a4e6fa8455a6625369998dd07f63a593377"],"state_sha256":"5181d209dba8d6bb832fd351f2e4cbe6f6184977418789220226e88e30d42650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WOsiqpVS9/cWEn3cAd5JPlxcnA7EkH567ySnqBXhOAGO1T5vUzERxn6JOO2b0Q+Nve319rLIANur/+NGtpHvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T04:48:45.329295Z","bundle_sha256":"c2f91ff5ef6cb22d4909c2f739050a6ea62b391c8e3fd105ca366fcb9b7ad950"}}