{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BZLTA3UVYKXVBBCWSXHDHLSAR6","short_pith_number":"pith:BZLTA3UV","canonical_record":{"source":{"id":"2505.07067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-11T17:38:40Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"229551290ac4d2b9cce6bd5e76b30f20fa563cbb8455df94438a22aad4f8c8db","abstract_canon_sha256":"98e845813f0d39c10cec34d8e902d034f653b4572c2bbf8955dbd68159eab4a8"},"schema_version":"1.0"},"canonical_sha256":"0e57306e95c2af50845695ce33ae408fbd2c0831d0e1a73be115023c4a3d00d9","source":{"kind":"arxiv","id":"2505.07067","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07067","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07067v1","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07067","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"BZLTA3UVYKXV","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"BZLTA3UVYKXVBBCW","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"BZLTA3UV","created_at":"2026-07-05T11:01:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BZLTA3UVYKXVBBCWSXHDHLSAR6","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-11T17:38:40Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"229551290ac4d2b9cce6bd5e76b30f20fa563cbb8455df94438a22aad4f8c8db","abstract_canon_sha256":"98e845813f0d39c10cec34d8e902d034f653b4572c2bbf8955dbd68159eab4a8"},"schema_version":"1.0"},"canonical_sha256":"0e57306e95c2af50845695ce33ae408fbd2c0831d0e1a73be115023c4a3d00d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:42.224350Z","signature_b64":"U0itwy+PqT4z5AtO2TJ1WQ1r0nJCNU3emKfAKiI4njNI12VW2KvDz+IX6EnjE7xjOFZ/bVD8oRmcHYiaPrz5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e57306e95c2af50845695ce33ae408fbd2c0831d0e1a73be115023c4a3d00d9","last_reissued_at":"2026-07-05T11:01:42.223848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:42.223848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07067","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":"2026-07-05T11:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ts85EWK5CAN+TVL69jblTWCmCEao6RlYbb+2PqKRtf7uu+8bgLXtzl+flGjUa4/yCzQLwkBXssj4UKtDdCaEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:12:19.077632Z"},"content_sha256":"ebd2a5ed94de5b6a9ade548c1978bbda46c6d3f41a1add63036de0a150408840","schema_version":"1.0","event_id":"sha256:ebd2a5ed94de5b6a9ade548c1978bbda46c6d3f41a1add63036de0a150408840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BZLTA3UVYKXVBBCWSXHDHLSAR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning curves theory for hierarchically compositional data with power-law distributed features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Francesco Cagnetta, Hyunmo Kang, Matthieu Wyart","submitted_at":"2025-05-11T17:38:40Z","abstract_excerpt":"Recent theories suggest that Neural Scaling Laws arise whenever the task is linearly decomposed into power-law distributed units. Alternatively, scaling laws also emerge when data exhibit a hierarchically compositional structure, as is thought to occur in language and images. To unify these views, we consider classification and next-token prediction tasks based on probabilistic context-free grammars -- probabilistic models that generate data via a hierarchy of production rules. For classification, we show that having power-law distributed production rules results in a power-law learning curve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07067","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/2505.07067/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":"2026-07-05T11:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGfJxbCnBqu6Sxv1CE4jIN4+JFLwiGSjNA3udqjfkAPrklqOS14RBj+hzvYjDe+LJMYxa33kwJv6RyHIChZTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:12:19.078058Z"},"content_sha256":"b53e57e55cc3d4dd7ca3af7b422ea98d5f1e6a7ca7db729ee3e2c87db06e006a","schema_version":"1.0","event_id":"sha256:b53e57e55cc3d4dd7ca3af7b422ea98d5f1e6a7ca7db729ee3e2c87db06e006a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/bundle.json","state_url":"https://pith.science/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/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":"2026-08-17T20:12:19Z","links":{"resolver":"https://pith.science/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6","bundle":"https://pith.science/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/bundle.json","state":"https://pith.science/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZLTA3UVYKXVBBCWSXHDHLSAR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BZLTA3UVYKXVBBCWSXHDHLSAR6","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":"98e845813f0d39c10cec34d8e902d034f653b4572c2bbf8955dbd68159eab4a8","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-11T17:38:40Z","title_canon_sha256":"229551290ac4d2b9cce6bd5e76b30f20fa563cbb8455df94438a22aad4f8c8db"},"schema_version":"1.0","source":{"id":"2505.07067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07067","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07067v1","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07067","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"BZLTA3UVYKXV","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"BZLTA3UVYKXVBBCW","created_at":"2026-07-05T11:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"BZLTA3UV","created_at":"2026-07-05T11:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:b53e57e55cc3d4dd7ca3af7b422ea98d5f1e6a7ca7db729ee3e2c87db06e006a","target":"graph","created_at":"2026-07-05T11:01:42Z","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/2505.07067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent theories suggest that Neural Scaling Laws arise whenever the task is linearly decomposed into power-law distributed units. Alternatively, scaling laws also emerge when data exhibit a hierarchically compositional structure, as is thought to occur in language and images. To unify these views, we consider classification and next-token prediction tasks based on probabilistic context-free grammars -- probabilistic models that generate data via a hierarchy of production rules. For classification, we show that having power-law distributed production rules results in a power-law learning curve ","authors_text":"Francesco Cagnetta, Hyunmo Kang, Matthieu Wyart","cross_cats":["cond-mat.dis-nn","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-11T17:38:40Z","title":"Learning curves theory for hierarchically compositional data with power-law distributed features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07067","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:ebd2a5ed94de5b6a9ade548c1978bbda46c6d3f41a1add63036de0a150408840","target":"record","created_at":"2026-07-05T11:01:42Z","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":"98e845813f0d39c10cec34d8e902d034f653b4572c2bbf8955dbd68159eab4a8","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-11T17:38:40Z","title_canon_sha256":"229551290ac4d2b9cce6bd5e76b30f20fa563cbb8455df94438a22aad4f8c8db"},"schema_version":"1.0","source":{"id":"2505.07067","kind":"arxiv","version":1}},"canonical_sha256":"0e57306e95c2af50845695ce33ae408fbd2c0831d0e1a73be115023c4a3d00d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e57306e95c2af50845695ce33ae408fbd2c0831d0e1a73be115023c4a3d00d9","first_computed_at":"2026-07-05T11:01:42.223848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:42.223848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U0itwy+PqT4z5AtO2TJ1WQ1r0nJCNU3emKfAKiI4njNI12VW2KvDz+IX6EnjE7xjOFZ/bVD8oRmcHYiaPrz5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:42.224350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebd2a5ed94de5b6a9ade548c1978bbda46c6d3f41a1add63036de0a150408840","sha256:b53e57e55cc3d4dd7ca3af7b422ea98d5f1e6a7ca7db729ee3e2c87db06e006a"],"state_sha256":"792010ea6f1dcc38e5c619f5af2a35bce2472945179a7f5e3b1fa4f999eaf301"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/zi+Dy3dj+W81qZBCuYtPog+S9ASLxNjL4wVm1A84f+bmXyvbjvuVApNMMePdoe71mSMjMpU9/ANo6iQG+7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:12:19.080671Z","bundle_sha256":"9617a8835de89330ee57ae40698b307992b1e1fccd9979ce393457fc6a64823d"}}