{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QG7C3XJ4P35YVLRAAQZ2DTI25Y","short_pith_number":"pith:QG7C3XJ4","canonical_record":{"source":{"id":"2608.03930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T17:02:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c19e2651cda1dd4c189cfa1035ec5f96f5a0c3e1c668cfa959f9f629300a698d","abstract_canon_sha256":"f15c485ecce04f4575baabde12f413c5da3d2aac78a595bfc98638a1388d177e"},"schema_version":"1.0"},"canonical_sha256":"81be2ddd3c7efb8aae200433a1cd1aee3763de19d4971dc06317f4f0f1c8ae49","source":{"kind":"arxiv","id":"2608.03930","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03930","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03930v1","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03930","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"QG7C3XJ4P35Y","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"QG7C3XJ4P35YVLRA","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"QG7C3XJ4","created_at":"2026-08-05T01:37:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QG7C3XJ4P35YVLRAAQZ2DTI25Y","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T17:02:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c19e2651cda1dd4c189cfa1035ec5f96f5a0c3e1c668cfa959f9f629300a698d","abstract_canon_sha256":"f15c485ecce04f4575baabde12f413c5da3d2aac78a595bfc98638a1388d177e"},"schema_version":"1.0"},"canonical_sha256":"81be2ddd3c7efb8aae200433a1cd1aee3763de19d4971dc06317f4f0f1c8ae49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:31.979419Z","signature_b64":"Ch3YUvAOjDx75X1vsq91TtDpASeBbJwX7AkgNMT1ayHDE6sUYf9sRs1VIYFVDu9MXkNpef8tA10i7ErjqZL9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81be2ddd3c7efb8aae200433a1cd1aee3763de19d4971dc06317f4f0f1c8ae49","last_reissued_at":"2026-08-05T01:37:31.977968Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:31.977968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03930","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":"2026-08-05T01:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4CalAEOupXhXxTVh3jMNygnQ0OsmzcWtRg8AeVDETopi0PbVnP8b+z5DHJ4RWpl2OZACnr2gRf6qvA8ofUVkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:54:34.921567Z"},"content_sha256":"01cb7b1b0b521e1c4a2a4af7168e01a4eb6f01e7b593529e6f6c1b11f1c71aa2","schema_version":"1.0","event_id":"sha256:01cb7b1b0b521e1c4a2a4af7168e01a4eb6f01e7b593529e6f6c1b11f1c71aa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QG7C3XJ4P35YVLRAAQZ2DTI25Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jo-Ku Cheng, Marco Valentino, Nikolaos Aletras","submitted_at":"2026-08-04T17:02:34Z","abstract_excerpt":"Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural algorithms, rely on narrow primitives that fail to capture the expressive capacity of natural language. Moreover, prior studies remain restricted to relatively small token budgets, offering limited insight into skill emergence and representational dynamics. To address these limitations, we propose logic pre-pretraining (Logic-PPT) as a principled initialization strategy, leveraging formal derivations to impart riche"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03930","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/2608.03930/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":"2026-08-05T01:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JMpNFfHeeSCoPLfCbN7g5gdT4ooACUrb3jFD1Or3f3F/CLiTXGm5kwT5h4beIbvsI4hqihP+ukN28XkjhYPtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:54:34.922304Z"},"content_sha256":"53242fbc7daad272cfbd2ac1dc45427a7f803a202effde08543b26143dc871ab","schema_version":"1.0","event_id":"sha256:53242fbc7daad272cfbd2ac1dc45427a7f803a202effde08543b26143dc871ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/bundle.json","state_url":"https://pith.science/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/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":"2026-08-17T04:54:34Z","links":{"resolver":"https://pith.science/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y","bundle":"https://pith.science/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/bundle.json","state":"https://pith.science/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QG7C3XJ4P35YVLRAAQZ2DTI25Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QG7C3XJ4P35YVLRAAQZ2DTI25Y","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":"f15c485ecce04f4575baabde12f413c5da3d2aac78a595bfc98638a1388d177e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T17:02:34Z","title_canon_sha256":"c19e2651cda1dd4c189cfa1035ec5f96f5a0c3e1c668cfa959f9f629300a698d"},"schema_version":"1.0","source":{"id":"2608.03930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03930","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03930v1","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03930","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"QG7C3XJ4P35Y","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"QG7C3XJ4P35YVLRA","created_at":"2026-08-05T01:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"QG7C3XJ4","created_at":"2026-08-05T01:37:31Z"}],"graph_snapshots":[{"event_id":"sha256:53242fbc7daad272cfbd2ac1dc45427a7f803a202effde08543b26143dc871ab","target":"graph","created_at":"2026-08-05T01:37:31Z","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/2608.03930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural algorithms, rely on narrow primitives that fail to capture the expressive capacity of natural language. Moreover, prior studies remain restricted to relatively small token budgets, offering limited insight into skill emergence and representational dynamics. To address these limitations, we propose logic pre-pretraining (Logic-PPT) as a principled initialization strategy, leveraging formal derivations to impart riche","authors_text":"Jo-Ku Cheng, Marco Valentino, Nikolaos Aletras","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T17:02:34Z","title":"Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03930","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":"sha256:01cb7b1b0b521e1c4a2a4af7168e01a4eb6f01e7b593529e6f6c1b11f1c71aa2","target":"record","created_at":"2026-08-05T01:37:31Z","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":"f15c485ecce04f4575baabde12f413c5da3d2aac78a595bfc98638a1388d177e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T17:02:34Z","title_canon_sha256":"c19e2651cda1dd4c189cfa1035ec5f96f5a0c3e1c668cfa959f9f629300a698d"},"schema_version":"1.0","source":{"id":"2608.03930","kind":"arxiv","version":1}},"canonical_sha256":"81be2ddd3c7efb8aae200433a1cd1aee3763de19d4971dc06317f4f0f1c8ae49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81be2ddd3c7efb8aae200433a1cd1aee3763de19d4971dc06317f4f0f1c8ae49","first_computed_at":"2026-08-05T01:37:31.977968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:31.977968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ch3YUvAOjDx75X1vsq91TtDpASeBbJwX7AkgNMT1ayHDE6sUYf9sRs1VIYFVDu9MXkNpef8tA10i7ErjqZL9DQ==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:31.979419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01cb7b1b0b521e1c4a2a4af7168e01a4eb6f01e7b593529e6f6c1b11f1c71aa2","sha256:53242fbc7daad272cfbd2ac1dc45427a7f803a202effde08543b26143dc871ab"],"state_sha256":"a20e37846e256af523b88ea0f17690461a72f8a4cead76f08a7185d76ddb95cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ODDLHW6JL2ubaw7BDSVzuGIoFZcnU/C3iezohHbQOKWpzbMYc1Uk649ItgJBydCgZizS5v+T7gZ5FkNXZT85DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:54:34.928180Z","bundle_sha256":"75c096af815e830624aea777a5f69caca74cd9ee396739295114bbd3db65e8dd"}}