{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZNEB7KKZ6PBAVMGB47T6LNGLGY","short_pith_number":"pith:ZNEB7KKZ","canonical_record":{"source":{"id":"2505.22308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"e68e84e9147ae14d48906f0878cceec10f2a7ab2f50efd9ffb740c6915fa347a","abstract_canon_sha256":"ffd20b57a1b34f68e006238ab6c40fd6953845db85dcfd5352209a839d8a2ea1"},"schema_version":"1.0"},"canonical_sha256":"cb481fa959f3c20ab0c1e7e7e5b4cb361d6bf9be9980ed5a2b7f12cc44b9d4ae","source":{"kind":"arxiv","id":"2505.22308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22308","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22308v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22308","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZNEB7KKZ6PBA","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZNEB7KKZ6PBAVMGB","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZNEB7KKZ","created_at":"2026-07-05T11:11:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZNEB7KKZ6PBAVMGB47T6LNGLGY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"e68e84e9147ae14d48906f0878cceec10f2a7ab2f50efd9ffb740c6915fa347a","abstract_canon_sha256":"ffd20b57a1b34f68e006238ab6c40fd6953845db85dcfd5352209a839d8a2ea1"},"schema_version":"1.0"},"canonical_sha256":"cb481fa959f3c20ab0c1e7e7e5b4cb361d6bf9be9980ed5a2b7f12cc44b9d4ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:12.969522Z","signature_b64":"e6CD5UKeV+FXcRbWGitLJnJaJbAVbHU40r/NvH8ANLXpCYBXkP6G2saa+jEPRk8sxVF/23CFzq3j8qKuyygJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb481fa959f3c20ab0c1e7e7e5b4cb361d6bf9be9980ed5a2b7f12cc44b9d4ae","last_reissued_at":"2026-07-05T11:11:12.969026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:12.969026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22308","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":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4HNG90NeCw2dzEsM6dJbHJp5ucdg4boh598mdt4ZtEdBn836DEGvHC2VbP3GJrzmika/ujiN2YEYXCnFewJdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:59:08.499671Z"},"content_sha256":"2e3a50527f2babc00e6a193039044a9cbcb33ffbc77a976236b3e0ac46bba1ab","schema_version":"1.0","event_id":"sha256:2e3a50527f2babc00e6a193039044a9cbcb33ffbc77a976236b3e0ac46bba1ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZNEB7KKZ6PBAVMGB47T6LNGLGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anton van den Hengel, Damien Teney, Hemanth Saratchandran, Liangze Jiang, Zachary Shinnick","submitted_at":"2025-05-28T12:50:09Z","abstract_excerpt":"Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the same benefits as natural language pretraining. It is unclear what specific capabilities such simple synthetic data instils in a model, where these capabilities reside in the architecture, and how they manifest within its weights. In this short paper, we identify several beneficial forms of procedural data, together with specific algorithmic reasoning skills "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22308","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/2505.22308/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":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9lpzEPTUhcR/hjz6yYeVKCLFOEB3e57RQCZICeSyVrV4s7TmI0L+5hS/lOHd+DqwDspUQfD1JOE2d+CWHvzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:59:08.500415Z"},"content_sha256":"01095d45ac31a85849d0b80732cd1e313a9a9604fcd657e4fdab1ccc9fa38439","schema_version":"1.0","event_id":"sha256:01095d45ac31a85849d0b80732cd1e313a9a9604fcd657e4fdab1ccc9fa38439"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/bundle.json","state_url":"https://pith.science/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/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":"2026-08-08T20:59:08Z","links":{"resolver":"https://pith.science/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY","bundle":"https://pith.science/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/bundle.json","state":"https://pith.science/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNEB7KKZ6PBAVMGB47T6LNGLGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZNEB7KKZ6PBAVMGB47T6LNGLGY","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":"ffd20b57a1b34f68e006238ab6c40fd6953845db85dcfd5352209a839d8a2ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:50:09Z","title_canon_sha256":"e68e84e9147ae14d48906f0878cceec10f2a7ab2f50efd9ffb740c6915fa347a"},"schema_version":"1.0","source":{"id":"2505.22308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22308","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22308v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22308","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZNEB7KKZ6PBA","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZNEB7KKZ6PBAVMGB","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZNEB7KKZ","created_at":"2026-07-05T11:11:12Z"}],"graph_snapshots":[{"event_id":"sha256:01095d45ac31a85849d0b80732cd1e313a9a9604fcd657e4fdab1ccc9fa38439","target":"graph","created_at":"2026-07-05T11:11:12Z","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/2505.22308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the same benefits as natural language pretraining. It is unclear what specific capabilities such simple synthetic data instils in a model, where these capabilities reside in the architecture, and how they manifest within its weights. In this short paper, we identify several beneficial forms of procedural data, together with specific algorithmic reasoning skills ","authors_text":"Anton van den Hengel, Damien Teney, Hemanth Saratchandran, Liangze Jiang, Zachary Shinnick","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:50:09Z","title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22308","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":"sha256:2e3a50527f2babc00e6a193039044a9cbcb33ffbc77a976236b3e0ac46bba1ab","target":"record","created_at":"2026-07-05T11:11:12Z","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":"ffd20b57a1b34f68e006238ab6c40fd6953845db85dcfd5352209a839d8a2ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:50:09Z","title_canon_sha256":"e68e84e9147ae14d48906f0878cceec10f2a7ab2f50efd9ffb740c6915fa347a"},"schema_version":"1.0","source":{"id":"2505.22308","kind":"arxiv","version":1}},"canonical_sha256":"cb481fa959f3c20ab0c1e7e7e5b4cb361d6bf9be9980ed5a2b7f12cc44b9d4ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb481fa959f3c20ab0c1e7e7e5b4cb361d6bf9be9980ed5a2b7f12cc44b9d4ae","first_computed_at":"2026-07-05T11:11:12.969026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:12.969026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e6CD5UKeV+FXcRbWGitLJnJaJbAVbHU40r/NvH8ANLXpCYBXkP6G2saa+jEPRk8sxVF/23CFzq3j8qKuyygJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:12.969522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3a50527f2babc00e6a193039044a9cbcb33ffbc77a976236b3e0ac46bba1ab","sha256:01095d45ac31a85849d0b80732cd1e313a9a9604fcd657e4fdab1ccc9fa38439"],"state_sha256":"86fb75a39e98c9919df8b4a8e9819ce45c55b04a77a58aeb3ad32cc18706ce69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJ5+T5OZ1v8NIzPfhkpRgSmsEmrwl4GFbgTzCTdAesb761M0l4+cUZIMz4z5IXuxBiQhdMEUIpAkLIVMgwyyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:59:08.504147Z","bundle_sha256":"2181768fea4c41c698a3b3afeabc31a0c7998e4df326e4fe3834fd84783a6246"}}