{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7TJXN6N5AQCVSRTPAA354GXU2V","short_pith_number":"pith:7TJXN6N5","canonical_record":{"source":{"id":"2402.13512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T03:51:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f577128798fa4228aae5cf47bf9ceb264c7c0141c7328664ede3b6a9d8e88fbf","abstract_canon_sha256":"9abd1457837dbedb10b25fa998c3381070a811f14d7004243369fa8191a0ac90"},"schema_version":"1.0"},"canonical_sha256":"fcd376f9bd040559466f0037de1af4d553c3a07a891cba15810a0f19082a5289","source":{"kind":"arxiv","id":"2402.13512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13512","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13512v1","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13512","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"7TJXN6N5AQCV","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"7TJXN6N5AQCVSRTP","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"7TJXN6N5","created_at":"2026-07-05T07:47:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7TJXN6N5AQCVSRTPAA354GXU2V","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T03:51:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f577128798fa4228aae5cf47bf9ceb264c7c0141c7328664ede3b6a9d8e88fbf","abstract_canon_sha256":"9abd1457837dbedb10b25fa998c3381070a811f14d7004243369fa8191a0ac90"},"schema_version":"1.0"},"canonical_sha256":"fcd376f9bd040559466f0037de1af4d553c3a07a891cba15810a0f19082a5289","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:33.550013Z","signature_b64":"oR/oStuDG2JbyxrvCLIBGnZZ6RJdr35fyTMK4l6eKuMJUNlgYoXFWtM8Xn005XQIOeo1j2ghIVA/2+XcaKukCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd376f9bd040559466f0037de1af4d553c3a07a891cba15810a0f19082a5289","last_reissued_at":"2026-07-05T07:47:33.549550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:33.549550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13512","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":"2026-07-05T07:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKA/DO119CsSGKWQNR6hpgmkzJK+LGcAk7DL/3lyrJxtwpd5Sc90cwCoaUKT6XJcXVx9SAOkp9GfPS3GCUDWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:32.064521Z"},"content_sha256":"432fa9d0e68dc8a05763e8b3d3f97d9da817936f390e201089f853d6e66d31e2","schema_version":"1.0","event_id":"sha256:432fa9d0e68dc8a05763e8b3d3f97d9da817936f390e201089f853d6e66d31e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7TJXN6N5AQCVSRTPAA354GXU2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankit Singh Rawat, M. Emrullah Ildiz, Samet Oymak, Yingcong Li, Yixiao Huang","submitted_at":"2024-02-21T03:51:34Z","abstract_excerpt":"Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and associated output data sampled from the model. We first establish a precise mapping between the self-attention mechanism and Markov models: Inputting a prompt to the model samples the output token according to a context-conditioned Markov chain (CCMC) which weights the transition matrix of a base Markov chain. Additionally, incorporating positional encoding results in p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13512","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/2402.13512/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":"2026-07-05T07:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvIBXUBk95rAs3PVXHJ2bDYeFEJ/HQhhwAobJFjckc9oJ8Rbk+OLE+CEn0ascgQv/e81FkjJhyc3h842FF4uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:32.067024Z"},"content_sha256":"6ccee6a91c89930387630046a25dc987d46c880a31228ea8a2f743f762ebd470","schema_version":"1.0","event_id":"sha256:6ccee6a91c89930387630046a25dc987d46c880a31228ea8a2f743f762ebd470"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TJXN6N5AQCVSRTPAA354GXU2V/bundle.json","state_url":"https://pith.science/pith/7TJXN6N5AQCVSRTPAA354GXU2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TJXN6N5AQCVSRTPAA354GXU2V/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":"2026-08-11T02:20:32Z","links":{"resolver":"https://pith.science/pith/7TJXN6N5AQCVSRTPAA354GXU2V","bundle":"https://pith.science/pith/7TJXN6N5AQCVSRTPAA354GXU2V/bundle.json","state":"https://pith.science/pith/7TJXN6N5AQCVSRTPAA354GXU2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TJXN6N5AQCVSRTPAA354GXU2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7TJXN6N5AQCVSRTPAA354GXU2V","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":"9abd1457837dbedb10b25fa998c3381070a811f14d7004243369fa8191a0ac90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T03:51:34Z","title_canon_sha256":"f577128798fa4228aae5cf47bf9ceb264c7c0141c7328664ede3b6a9d8e88fbf"},"schema_version":"1.0","source":{"id":"2402.13512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13512","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13512v1","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13512","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"7TJXN6N5AQCV","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"7TJXN6N5AQCVSRTP","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"7TJXN6N5","created_at":"2026-07-05T07:47:33Z"}],"graph_snapshots":[{"event_id":"sha256:6ccee6a91c89930387630046a25dc987d46c880a31228ea8a2f743f762ebd470","target":"graph","created_at":"2026-07-05T07:47:33Z","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/2402.13512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and associated output data sampled from the model. We first establish a precise mapping between the self-attention mechanism and Markov models: Inputting a prompt to the model samples the output token according to a context-conditioned Markov chain (CCMC) which weights the transition matrix of a base Markov chain. Additionally, incorporating positional encoding results in p","authors_text":"Ankit Singh Rawat, M. Emrullah Ildiz, Samet Oymak, Yingcong Li, Yixiao Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T03:51:34Z","title":"From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13512","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":"sha256:432fa9d0e68dc8a05763e8b3d3f97d9da817936f390e201089f853d6e66d31e2","target":"record","created_at":"2026-07-05T07:47:33Z","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":"9abd1457837dbedb10b25fa998c3381070a811f14d7004243369fa8191a0ac90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T03:51:34Z","title_canon_sha256":"f577128798fa4228aae5cf47bf9ceb264c7c0141c7328664ede3b6a9d8e88fbf"},"schema_version":"1.0","source":{"id":"2402.13512","kind":"arxiv","version":1}},"canonical_sha256":"fcd376f9bd040559466f0037de1af4d553c3a07a891cba15810a0f19082a5289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcd376f9bd040559466f0037de1af4d553c3a07a891cba15810a0f19082a5289","first_computed_at":"2026-07-05T07:47:33.549550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:33.549550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oR/oStuDG2JbyxrvCLIBGnZZ6RJdr35fyTMK4l6eKuMJUNlgYoXFWtM8Xn005XQIOeo1j2ghIVA/2+XcaKukCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:33.550013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432fa9d0e68dc8a05763e8b3d3f97d9da817936f390e201089f853d6e66d31e2","sha256:6ccee6a91c89930387630046a25dc987d46c880a31228ea8a2f743f762ebd470"],"state_sha256":"40a2d93e1479dd08088d9b4882935488ded4cd2cf93a4af8b4f4741f7016e847"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"peNqIFoLzDjsapwe+Pqsl5SCUiR4YevdTJtXBy5BPxBclrHaW4wjmX01hVDvTrAPouciy1eJyrlWKoC2SoSzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:20:32.153325Z","bundle_sha256":"4807fc56a2b4b7e618f58a5fb01a15606456601bcb2dcc90de5f291c18527df7"}}