{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5NGXKHD4QXBV4ON4TTLDXI5PVD","short_pith_number":"pith:5NGXKHD4","canonical_record":{"source":{"id":"2504.09184","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T11:44:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c7acf9266fa691020b05a7e587375627a1a6dbb229cc1bed0d1d7e342f53da6","abstract_canon_sha256":"7b811445f78496df4f65c655471acc9624b6829865a86f799af60dfdc44d9d56"},"schema_version":"1.0"},"canonical_sha256":"eb4d751c7c85c35e39bc9cd63ba3afa8d1d341a45317bd2f4f5eeafa8328e6d4","source":{"kind":"arxiv","id":"2504.09184","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09184","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09184v3","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09184","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"5NGXKHD4QXBV","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"5NGXKHD4QXBV4ON4","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"5NGXKHD4","created_at":"2026-07-05T11:13:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5NGXKHD4QXBV4ON4TTLDXI5PVD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09184","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T11:44:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c7acf9266fa691020b05a7e587375627a1a6dbb229cc1bed0d1d7e342f53da6","abstract_canon_sha256":"7b811445f78496df4f65c655471acc9624b6829865a86f799af60dfdc44d9d56"},"schema_version":"1.0"},"canonical_sha256":"eb4d751c7c85c35e39bc9cd63ba3afa8d1d341a45317bd2f4f5eeafa8328e6d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:24.039780Z","signature_b64":"dPCjkKWiRwJdwsQ2pDVSDofQ7XuIf7miebFi6Bi4DPA66Yh+B0BO4pdjZjKWIhGirYudA0XnYBqTjq92eYjWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4d751c7c85c35e39bc9cd63ba3afa8d1d341a45317bd2f4f5eeafa8328e6d4","last_reissued_at":"2026-07-05T11:13:24.039257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:24.039257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09184","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":"2026-07-05T11:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hbGNK7YyJccghkM6UwVUiHM3xqtrqHAbzSbjwh+ZItr7wktmsNE9TUSXGKLYHP3OOCvtFpixa5X2tKj0vYRoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:16:33.852618Z"},"content_sha256":"dd20fc634ba142869a8e86c2178493dd2a8ada3c8d64de8970bf81fb320d0a49","schema_version":"1.0","event_id":"sha256:dd20fc634ba142869a8e86c2178493dd2a8ada3c8d64de8970bf81fb320d0a49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5NGXKHD4QXBV4ON4TTLDXI5PVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameterized Synthetic Text Generation with SimpleStories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chandan Sreedhara, Dan Braun, Emerald Zhang, Juan Diego Rodriguez, Lennart Finke, Mat Allen, Noa Nabeshima, Thomas Dooms, Thomas Marshall","submitted_at":"2025-04-12T11:44:47Z","abstract_excerpt":"We present SimpleStories, a large synthetic story dataset in simple language, consisting of 2 million samples each in English and Japanese. Through parameterizing prompts at multiple levels of abstraction, we achieve control over story characteristics at scale, inducing syntactic and semantic diversity. Ablations on a newly trained model suite show improved sample efficiency and model interpretability compared to the TinyStories dataset. We open-source all constituent parts of model creation, hoping to enable novel ways to study the end-to-end training process. As a byproduct, we move the fron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09184","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/2504.09184/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":"2026-07-05T11:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEiHVzR5I+knWZLH2dvcoFDxH6QRuFOnV27G84HS2U4T++cFvdJI0pDuveK6KWwbFn6fmGZd+xIR9PNhA1FMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:16:33.853620Z"},"content_sha256":"5b066caa84e86805ba29d77baf6a06bac6b27f63b04d89008c7c0155136fb6d7","schema_version":"1.0","event_id":"sha256:5b066caa84e86805ba29d77baf6a06bac6b27f63b04d89008c7c0155136fb6d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/bundle.json","state_url":"https://pith.science/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/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":"2026-08-07T00:16:33Z","links":{"resolver":"https://pith.science/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD","bundle":"https://pith.science/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/bundle.json","state":"https://pith.science/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NGXKHD4QXBV4ON4TTLDXI5PVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5NGXKHD4QXBV4ON4TTLDXI5PVD","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":"7b811445f78496df4f65c655471acc9624b6829865a86f799af60dfdc44d9d56","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T11:44:47Z","title_canon_sha256":"4c7acf9266fa691020b05a7e587375627a1a6dbb229cc1bed0d1d7e342f53da6"},"schema_version":"1.0","source":{"id":"2504.09184","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09184","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09184v3","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09184","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"5NGXKHD4QXBV","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"5NGXKHD4QXBV4ON4","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"5NGXKHD4","created_at":"2026-07-05T11:13:24Z"}],"graph_snapshots":[{"event_id":"sha256:5b066caa84e86805ba29d77baf6a06bac6b27f63b04d89008c7c0155136fb6d7","target":"graph","created_at":"2026-07-05T11:13:24Z","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/2504.09184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SimpleStories, a large synthetic story dataset in simple language, consisting of 2 million samples each in English and Japanese. Through parameterizing prompts at multiple levels of abstraction, we achieve control over story characteristics at scale, inducing syntactic and semantic diversity. Ablations on a newly trained model suite show improved sample efficiency and model interpretability compared to the TinyStories dataset. We open-source all constituent parts of model creation, hoping to enable novel ways to study the end-to-end training process. As a byproduct, we move the fron","authors_text":"Chandan Sreedhara, Dan Braun, Emerald Zhang, Juan Diego Rodriguez, Lennart Finke, Mat Allen, Noa Nabeshima, Thomas Dooms, Thomas Marshall","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T11:44:47Z","title":"Parameterized Synthetic Text Generation with SimpleStories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09184","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:dd20fc634ba142869a8e86c2178493dd2a8ada3c8d64de8970bf81fb320d0a49","target":"record","created_at":"2026-07-05T11:13:24Z","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":"7b811445f78496df4f65c655471acc9624b6829865a86f799af60dfdc44d9d56","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T11:44:47Z","title_canon_sha256":"4c7acf9266fa691020b05a7e587375627a1a6dbb229cc1bed0d1d7e342f53da6"},"schema_version":"1.0","source":{"id":"2504.09184","kind":"arxiv","version":3}},"canonical_sha256":"eb4d751c7c85c35e39bc9cd63ba3afa8d1d341a45317bd2f4f5eeafa8328e6d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb4d751c7c85c35e39bc9cd63ba3afa8d1d341a45317bd2f4f5eeafa8328e6d4","first_computed_at":"2026-07-05T11:13:24.039257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:24.039257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dPCjkKWiRwJdwsQ2pDVSDofQ7XuIf7miebFi6Bi4DPA66Yh+B0BO4pdjZjKWIhGirYudA0XnYBqTjq92eYjWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:24.039780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09184","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd20fc634ba142869a8e86c2178493dd2a8ada3c8d64de8970bf81fb320d0a49","sha256:5b066caa84e86805ba29d77baf6a06bac6b27f63b04d89008c7c0155136fb6d7"],"state_sha256":"445d1442607ad5e012dd585925ada9d27f98e4ac55a111394456d4a630d6eeab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WZyHwOWCyt+OtXE6UOON4dPulOGhLYpOL7uesmU0wYTgaFBnX7rU3Ws0HVooUIv9hbqHgM4jTaauoxVCnbnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:16:33.882322Z","bundle_sha256":"cfb1c09e238631be57d57b74b831dff6376b62a12326368f065288f00dbd921b"}}