{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W4GZ7EK6UGGKYL7B2MFQF36JDT","short_pith_number":"pith:W4GZ7EK6","canonical_record":{"source":{"id":"2502.19249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:55:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8ad1e390fc1f11a6bb4b94874c2189255b03c573aeca4bfe1073bd86107d4384","abstract_canon_sha256":"1384bd3bd6c2cf5f36b4e3aeb57cc9911745467c8907c999d367fd93756dc4e1"},"schema_version":"1.0"},"canonical_sha256":"b70d9f915ea18cac2fe1d30b02efc91cfbf324775f36e7240c5c21e8880d6614","source":{"kind":"arxiv","id":"2502.19249","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19249","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19249v2","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19249","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"W4GZ7EK6UGGK","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"W4GZ7EK6UGGKYL7B","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"W4GZ7EK6","created_at":"2026-07-05T11:10:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W4GZ7EK6UGGKYL7B2MFQF36JDT","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:55:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8ad1e390fc1f11a6bb4b94874c2189255b03c573aeca4bfe1073bd86107d4384","abstract_canon_sha256":"1384bd3bd6c2cf5f36b4e3aeb57cc9911745467c8907c999d367fd93756dc4e1"},"schema_version":"1.0"},"canonical_sha256":"b70d9f915ea18cac2fe1d30b02efc91cfbf324775f36e7240c5c21e8880d6614","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:05.832455Z","signature_b64":"JIy5PRiSm9Ulg/lmeslOHJgUK224S8j/SsBF2S02vxMVJ6+Nmr5jxc7jUfrqLGgOKm3MnymlE4a4lReKbXFmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b70d9f915ea18cac2fe1d30b02efc91cfbf324775f36e7240c5c21e8880d6614","last_reissued_at":"2026-07-05T11:10:05.831920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:05.831920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19249","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":"2026-07-05T11:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+HP20/8aTeMrtu1tilkgFAMokgkk0QFeW9R6o80KyCXBqQyyQAYiWm/8V+nXd9ZuECMRb1FYcf14cQe44yjFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:09:44.831727Z"},"content_sha256":"f13279236aefdb018327e561b98bc67d51331e6fe3b011c60bdd53e225ab4a1b","schema_version":"1.0","event_id":"sha256:f13279236aefdb018327e561b98bc67d51331e6fe3b011c60bdd53e225ab4a1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W4GZ7EK6UGGKYL7B2MFQF36JDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuan Shi, Jackson Petty, Michael Y. Hu, Tal Linzen, William Merrill","submitted_at":"2025-02-26T15:55:55Z","abstract_excerpt":"Pretraining language models on formal language can improve their acquisition of natural language. Which features of the formal language impart an inductive bias that leads to effective transfer? Drawing on insights from linguistics and complexity theory, we hypothesize that effective transfer occurs when two conditions are met: the formal language should capture the dependency structures present in natural language, and it should remain within the computational limitations of the model architecture. We experiment with pre-pretraining (training on formal language before natural languages) on tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19249","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/2502.19249/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":"2026-07-05T11:10:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wuGpKdQttjnBGxY31iIHZG/5EwVpb27BGauZJ77AbwtMwOgFgnLMv9VVRIVuOpBKI27XRKmVrxSUnRS0lcDhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:09:44.832244Z"},"content_sha256":"c6647c436c91d8cb535c4137f05e2412f4643257e5d543d2168833b545e27a5b","schema_version":"1.0","event_id":"sha256:c6647c436c91d8cb535c4137f05e2412f4643257e5d543d2168833b545e27a5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/bundle.json","state_url":"https://pith.science/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/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":"2026-08-06T09:09:44Z","links":{"resolver":"https://pith.science/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT","bundle":"https://pith.science/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/bundle.json","state":"https://pith.science/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4GZ7EK6UGGKYL7B2MFQF36JDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W4GZ7EK6UGGKYL7B2MFQF36JDT","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":"1384bd3bd6c2cf5f36b4e3aeb57cc9911745467c8907c999d367fd93756dc4e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:55:55Z","title_canon_sha256":"8ad1e390fc1f11a6bb4b94874c2189255b03c573aeca4bfe1073bd86107d4384"},"schema_version":"1.0","source":{"id":"2502.19249","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19249","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19249v2","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19249","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"W4GZ7EK6UGGK","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"W4GZ7EK6UGGKYL7B","created_at":"2026-07-05T11:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"W4GZ7EK6","created_at":"2026-07-05T11:10:05Z"}],"graph_snapshots":[{"event_id":"sha256:c6647c436c91d8cb535c4137f05e2412f4643257e5d543d2168833b545e27a5b","target":"graph","created_at":"2026-07-05T11:10:05Z","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/2502.19249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining language models on formal language can improve their acquisition of natural language. Which features of the formal language impart an inductive bias that leads to effective transfer? Drawing on insights from linguistics and complexity theory, we hypothesize that effective transfer occurs when two conditions are met: the formal language should capture the dependency structures present in natural language, and it should remain within the computational limitations of the model architecture. We experiment with pre-pretraining (training on formal language before natural languages) on tr","authors_text":"Chuan Shi, Jackson Petty, Michael Y. Hu, Tal Linzen, William Merrill","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:55:55Z","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19249","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:f13279236aefdb018327e561b98bc67d51331e6fe3b011c60bdd53e225ab4a1b","target":"record","created_at":"2026-07-05T11:10:05Z","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":"1384bd3bd6c2cf5f36b4e3aeb57cc9911745467c8907c999d367fd93756dc4e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T15:55:55Z","title_canon_sha256":"8ad1e390fc1f11a6bb4b94874c2189255b03c573aeca4bfe1073bd86107d4384"},"schema_version":"1.0","source":{"id":"2502.19249","kind":"arxiv","version":2}},"canonical_sha256":"b70d9f915ea18cac2fe1d30b02efc91cfbf324775f36e7240c5c21e8880d6614","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b70d9f915ea18cac2fe1d30b02efc91cfbf324775f36e7240c5c21e8880d6614","first_computed_at":"2026-07-05T11:10:05.831920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:05.831920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JIy5PRiSm9Ulg/lmeslOHJgUK224S8j/SsBF2S02vxMVJ6+Nmr5jxc7jUfrqLGgOKm3MnymlE4a4lReKbXFmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:05.832455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19249","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f13279236aefdb018327e561b98bc67d51331e6fe3b011c60bdd53e225ab4a1b","sha256:c6647c436c91d8cb535c4137f05e2412f4643257e5d543d2168833b545e27a5b"],"state_sha256":"dcfa1a99ded5f2db40c651b4b53a060b3e35c9bc3cf57c5f3ea7262c15e62695"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngMHPlqGcHetgKZeWMRAyrKJqoiRpliiEqxGvuqNQPWeWQf8xR2bApGbqgyblrM1UOXFG+ac0oefWAUaWYc/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:09:44.836619Z","bundle_sha256":"cdf3f1fe154f9d082cc805ed77178ff943b70182dd43b260a5aa8935290d72bc"}}