{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YJCJARO5FJAK7XS3PPW2VBTR24","short_pith_number":"pith:YJCJARO5","canonical_record":{"source":{"id":"2407.12034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T22:18:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4df864e126d4eaeb05e085aac583c70bb1b9a0afd4c3b2f4f44385bdccc550d3","abstract_canon_sha256":"ccb225c8fd897630fc399e4f3c972221c7d7dc9bc0e41e9973e2bc2b5bcfb4e3"},"schema_version":"1.0"},"canonical_sha256":"c2449045dd2a40afde5b7bedaa8671d73c178ef88e7ae855d1a467659c2f4be9","source":{"kind":"arxiv","id":"2407.12034","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12034","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12034v2","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12034","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_12","alias_value":"YJCJARO5FJAK","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"YJCJARO5FJAK7XS3","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"YJCJARO5","created_at":"2026-07-05T09:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YJCJARO5FJAK7XS3PPW2VBTR24","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T22:18:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4df864e126d4eaeb05e085aac583c70bb1b9a0afd4c3b2f4f44385bdccc550d3","abstract_canon_sha256":"ccb225c8fd897630fc399e4f3c972221c7d7dc9bc0e41e9973e2bc2b5bcfb4e3"},"schema_version":"1.0"},"canonical_sha256":"c2449045dd2a40afde5b7bedaa8671d73c178ef88e7ae855d1a467659c2f4be9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:05.807236Z","signature_b64":"XGgIrmZ7vEmmaqZl4Hm8Hjk7zufMUp+vY7HSrucPcK91WVJrNIVWm/ej3qwt98sbvSUUkbAeHDdAwGxd+pRLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2449045dd2a40afde5b7bedaa8671d73c178ef88e7ae855d1a467659c2f4be9","last_reissued_at":"2026-07-05T09:31:05.806786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:05.806786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12034","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":"2026-07-05T09:31:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EA1od+ZBLYqyMm63/QW1PRWtaxRlfag8WQ1vaeHElygRcyuR4baCtdtEZtkKY9NDPe82UoRXoSFwdcNjNNwsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:34:53.748019Z"},"content_sha256":"95f3be179f314ff1fb227573a8e64cee7abf48089b51dcf53a1e352b57189bda","schema_version":"1.0","event_id":"sha256:95f3be179f314ff1fb227573a8e64cee7abf48089b51dcf53a1e352b57189bda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YJCJARO5FJAK7XS3PPW2VBTR24","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Transformers via N-gram Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Timothy Nguyen","submitted_at":"2024-06-30T22:18:49Z","abstract_excerpt":"Transformer based large-language models (LLMs) display extreme proficiency with language yet a precise understanding of how they work remains elusive. One way of demystifying transformer predictions would be to describe how they depend on their context in terms of simple template functions. This paper takes a first step in this direction by considering families of functions (i.e. rules) formed out of simple N-gram based statistics of the training data. By studying how well these rulesets approximate transformer predictions, we obtain a variety of novel discoveries: a simple method to detect ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12034","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/2407.12034/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":"2026-07-05T09:31:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aHSnYSjRyhgaVpJDaxMCCg5XiiAI7DKargsKhSQ3Tgynx4y+BB4aHugnRV6Hgtbl3d6f9TIRFsW8mTpAc1imAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:34:53.748675Z"},"content_sha256":"9bfc3d66a5f35663389acaecc2cd7bdae0cd5127ae33b2b4fe0b9131e4bcc394","schema_version":"1.0","event_id":"sha256:9bfc3d66a5f35663389acaecc2cd7bdae0cd5127ae33b2b4fe0b9131e4bcc394"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJCJARO5FJAK7XS3PPW2VBTR24/bundle.json","state_url":"https://pith.science/pith/YJCJARO5FJAK7XS3PPW2VBTR24/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJCJARO5FJAK7XS3PPW2VBTR24/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":"2026-08-19T11:34:53Z","links":{"resolver":"https://pith.science/pith/YJCJARO5FJAK7XS3PPW2VBTR24","bundle":"https://pith.science/pith/YJCJARO5FJAK7XS3PPW2VBTR24/bundle.json","state":"https://pith.science/pith/YJCJARO5FJAK7XS3PPW2VBTR24/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJCJARO5FJAK7XS3PPW2VBTR24/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJCJARO5FJAK7XS3PPW2VBTR24","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":"ccb225c8fd897630fc399e4f3c972221c7d7dc9bc0e41e9973e2bc2b5bcfb4e3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T22:18:49Z","title_canon_sha256":"4df864e126d4eaeb05e085aac583c70bb1b9a0afd4c3b2f4f44385bdccc550d3"},"schema_version":"1.0","source":{"id":"2407.12034","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12034","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12034v2","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12034","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_12","alias_value":"YJCJARO5FJAK","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"YJCJARO5FJAK7XS3","created_at":"2026-07-05T09:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"YJCJARO5","created_at":"2026-07-05T09:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:9bfc3d66a5f35663389acaecc2cd7bdae0cd5127ae33b2b4fe0b9131e4bcc394","target":"graph","created_at":"2026-07-05T09:31:05Z","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/2407.12034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer based large-language models (LLMs) display extreme proficiency with language yet a precise understanding of how they work remains elusive. One way of demystifying transformer predictions would be to describe how they depend on their context in terms of simple template functions. This paper takes a first step in this direction by considering families of functions (i.e. rules) formed out of simple N-gram based statistics of the training data. By studying how well these rulesets approximate transformer predictions, we obtain a variety of novel discoveries: a simple method to detect ov","authors_text":"Timothy Nguyen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T22:18:49Z","title":"Understanding Transformers via N-gram Statistics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12034","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":"sha256:95f3be179f314ff1fb227573a8e64cee7abf48089b51dcf53a1e352b57189bda","target":"record","created_at":"2026-07-05T09:31:05Z","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":"ccb225c8fd897630fc399e4f3c972221c7d7dc9bc0e41e9973e2bc2b5bcfb4e3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-30T22:18:49Z","title_canon_sha256":"4df864e126d4eaeb05e085aac583c70bb1b9a0afd4c3b2f4f44385bdccc550d3"},"schema_version":"1.0","source":{"id":"2407.12034","kind":"arxiv","version":2}},"canonical_sha256":"c2449045dd2a40afde5b7bedaa8671d73c178ef88e7ae855d1a467659c2f4be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2449045dd2a40afde5b7bedaa8671d73c178ef88e7ae855d1a467659c2f4be9","first_computed_at":"2026-07-05T09:31:05.806786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:05.806786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XGgIrmZ7vEmmaqZl4Hm8Hjk7zufMUp+vY7HSrucPcK91WVJrNIVWm/ej3qwt98sbvSUUkbAeHDdAwGxd+pRLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:05.807236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12034","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95f3be179f314ff1fb227573a8e64cee7abf48089b51dcf53a1e352b57189bda","sha256:9bfc3d66a5f35663389acaecc2cd7bdae0cd5127ae33b2b4fe0b9131e4bcc394"],"state_sha256":"0a49dcb587c98a7221671efe2c4ec862775c7581908ab8fd4701502c27fa6e53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDcHKePHGyUcBCEpDReLsAosXg2hjwbnzphaPWB8tbt3vmeruuvlTnubzvKI8olD3LZVuG3xRCIMF5WQptrLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:34:53.754164Z","bundle_sha256":"714c8574fe4ffaf2e676865871fb7b83ec68fd89c968cdc77804c1cc1e525084"}}