{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U46NP3PI7EGH6BV7HONS5WP5YK","short_pith_number":"pith:U46NP3PI","canonical_record":{"source":{"id":"2504.20752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T13:33:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6c23e1dd87bbbd2cc8741026054f8568e439e38e41e84894815d907930e22ff","abstract_canon_sha256":"4736e9458123248c1dbb640e663ccb49dac5519ac50554573adadfc1810d7dc7"},"schema_version":"1.0"},"canonical_sha256":"a73cd7ede8f90c7f06bf3b9b2ed9fdc2949b39d59d3416e9ba2a26f6879081ca","source":{"kind":"arxiv","id":"2504.20752","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20752","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20752v2","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20752","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"U46NP3PI7EGH","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_16","alias_value":"U46NP3PI7EGH6BV7","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_8","alias_value":"U46NP3PI","created_at":"2026-07-05T10:59:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U46NP3PI7EGH6BV7HONS5WP5YK","target":"record","payload":{"canonical_record":{"source":{"id":"2504.20752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T13:33:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6c23e1dd87bbbd2cc8741026054f8568e439e38e41e84894815d907930e22ff","abstract_canon_sha256":"4736e9458123248c1dbb640e663ccb49dac5519ac50554573adadfc1810d7dc7"},"schema_version":"1.0"},"canonical_sha256":"a73cd7ede8f90c7f06bf3b9b2ed9fdc2949b39d59d3416e9ba2a26f6879081ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:29.298962Z","signature_b64":"2F7R+zGyZl7+k8xNrbxvtEe2e5O0XmPPEM/bZR7sbhWnhmDL6ZH4pVPIsV4hMuA0bIjaB1jiVzvsiMCPL1WKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a73cd7ede8f90c7f06bf3b9b2ed9fdc2949b39d59d3416e9ba2a26f6879081ca","last_reissued_at":"2026-07-05T10:59:29.298439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:29.298439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.20752","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":"2026-07-05T10:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ojku9P+vdgrEjfra3IfaZpFuElAUzQTg6UxPpu5/HINp0HlVatTcF/rnCfBTrp2wMwkaHgzeW7c7rNC6AAoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:34:10.845597Z"},"content_sha256":"059737a74f21fbdbcb1cfddcb1e39e1b61ed92c71120c1e5b43dec407ccbe82e","schema_version":"1.0","event_id":"sha256:059737a74f21fbdbcb1cfddcb1e39e1b61ed92c71120c1e5b43dec407ccbe82e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U46NP3PI7EGH6BV7HONS5WP5YK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Felix Steinbauer, Gjergji Kasneci, Roman Abramov","submitted_at":"2025-04-29T13:33:29Z","abstract_excerpt":"Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural networks can transition from memorizing to perfectly generalizing once they detect underlying logical patterns - yet these studies have primarily used small, synthetic tasks. In this paper, for the first time, we extend grokking to real-world factual data and address the challenge of dataset sparsity by augmenting existing knowledge graphs with carefully desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20752","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/2504.20752/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":"2026-07-05T10:59:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zy6wD1Pu1vr31xSKNkPoECRkK5FxfSWPfyDvm8CBbcMyB9fEBBeg68nvmSLd8knMwOXIVhV3F5AxjJFdztDECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:34:10.846356Z"},"content_sha256":"4de45afefb4b4c80564fc9f8a1d94e786029bcd94d8b1421538df9ae55faf2b4","schema_version":"1.0","event_id":"sha256:4de45afefb4b4c80564fc9f8a1d94e786029bcd94d8b1421538df9ae55faf2b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U46NP3PI7EGH6BV7HONS5WP5YK/bundle.json","state_url":"https://pith.science/pith/U46NP3PI7EGH6BV7HONS5WP5YK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U46NP3PI7EGH6BV7HONS5WP5YK/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":"2026-08-19T09:34:10Z","links":{"resolver":"https://pith.science/pith/U46NP3PI7EGH6BV7HONS5WP5YK","bundle":"https://pith.science/pith/U46NP3PI7EGH6BV7HONS5WP5YK/bundle.json","state":"https://pith.science/pith/U46NP3PI7EGH6BV7HONS5WP5YK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U46NP3PI7EGH6BV7HONS5WP5YK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U46NP3PI7EGH6BV7HONS5WP5YK","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":"4736e9458123248c1dbb640e663ccb49dac5519ac50554573adadfc1810d7dc7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T13:33:29Z","title_canon_sha256":"d6c23e1dd87bbbd2cc8741026054f8568e439e38e41e84894815d907930e22ff"},"schema_version":"1.0","source":{"id":"2504.20752","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20752","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20752v2","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20752","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_12","alias_value":"U46NP3PI7EGH","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_16","alias_value":"U46NP3PI7EGH6BV7","created_at":"2026-07-05T10:59:29Z"},{"alias_kind":"pith_short_8","alias_value":"U46NP3PI","created_at":"2026-07-05T10:59:29Z"}],"graph_snapshots":[{"event_id":"sha256:4de45afefb4b4c80564fc9f8a1d94e786029bcd94d8b1421538df9ae55faf2b4","target":"graph","created_at":"2026-07-05T10:59:29Z","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/2504.20752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural networks can transition from memorizing to perfectly generalizing once they detect underlying logical patterns - yet these studies have primarily used small, synthetic tasks. In this paper, for the first time, we extend grokking to real-world factual data and address the challenge of dataset sparsity by augmenting existing knowledge graphs with carefully desi","authors_text":"Felix Steinbauer, Gjergji Kasneci, Roman Abramov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T13:33:29Z","title":"Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20752","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":"sha256:059737a74f21fbdbcb1cfddcb1e39e1b61ed92c71120c1e5b43dec407ccbe82e","target":"record","created_at":"2026-07-05T10:59:29Z","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":"4736e9458123248c1dbb640e663ccb49dac5519ac50554573adadfc1810d7dc7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T13:33:29Z","title_canon_sha256":"d6c23e1dd87bbbd2cc8741026054f8568e439e38e41e84894815d907930e22ff"},"schema_version":"1.0","source":{"id":"2504.20752","kind":"arxiv","version":2}},"canonical_sha256":"a73cd7ede8f90c7f06bf3b9b2ed9fdc2949b39d59d3416e9ba2a26f6879081ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a73cd7ede8f90c7f06bf3b9b2ed9fdc2949b39d59d3416e9ba2a26f6879081ca","first_computed_at":"2026-07-05T10:59:29.298439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:29.298439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2F7R+zGyZl7+k8xNrbxvtEe2e5O0XmPPEM/bZR7sbhWnhmDL6ZH4pVPIsV4hMuA0bIjaB1jiVzvsiMCPL1WKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:29.298962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20752","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:059737a74f21fbdbcb1cfddcb1e39e1b61ed92c71120c1e5b43dec407ccbe82e","sha256:4de45afefb4b4c80564fc9f8a1d94e786029bcd94d8b1421538df9ae55faf2b4"],"state_sha256":"29d3334dc0710d8d92a4b4f310a73fccd2a2c6b6255cabb8068736f5c1708e8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0q3jed/vFZDozH5waZSgQ1avGcxz8H9i52RR8LICunj2YSLeujJ2D4TKAn7AzYWuPgwebjmzffoxr0LwIEQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:34:10.853809Z","bundle_sha256":"fe7fe8552cd9c10ac55245dfd2e9fbfdf85ae576c190d157b78b18371e9c6b6e"}}