{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K2VXUGNLT56WEDXBTV2GZ7AMQD","short_pith_number":"pith:K2VXUGNL","canonical_record":{"source":{"id":"2501.13779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T15:58:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86f94a12140fb795297baefac68ce20b0a823332fe4e45046caf84a57d76db7c","abstract_canon_sha256":"110f6bc41a140e82b68c1b09b7d56154397e1503d03043268742f24d19105101"},"schema_version":"1.0"},"canonical_sha256":"56ab7a19ab9f7d620ee19d746cfc0c80e1bca2caf615e798afc10bf6a6f6d682","source":{"kind":"arxiv","id":"2501.13779","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13779","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13779v2","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13779","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"K2VXUGNLT56W","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"K2VXUGNLT56WEDXB","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"K2VXUGNL","created_at":"2026-07-05T11:14:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K2VXUGNLT56WEDXBTV2GZ7AMQD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T15:58:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86f94a12140fb795297baefac68ce20b0a823332fe4e45046caf84a57d76db7c","abstract_canon_sha256":"110f6bc41a140e82b68c1b09b7d56154397e1503d03043268742f24d19105101"},"schema_version":"1.0"},"canonical_sha256":"56ab7a19ab9f7d620ee19d746cfc0c80e1bca2caf615e798afc10bf6a6f6d682","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:52.824640Z","signature_b64":"7R8oAVUVVRES7n9OVOwgJn3ZwyYly5tPjcHkSQbCWSCPwUZ6ZF68zCzh9B0j4VM94RARKJV0qCsmsifn65YwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ab7a19ab9f7d620ee19d746cfc0c80e1bca2caf615e798afc10bf6a6f6d682","last_reissued_at":"2026-07-05T11:14:52.824232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:52.824232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13779","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":"2026-07-05T11:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7NDnYKlRmoylElkNW9um2FveNoX9pyDH4DwRHBqJR4aQtX4cb5KVbPSnB97Ld4xVplZMTKbMBEb3xofyrNzqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:05:28.105744Z"},"content_sha256":"f3437371cc0f65644c126bd3838b96c8d77200122d543af0001b1bd1da97ca1d","schema_version":"1.0","event_id":"sha256:f3437371cc0f65644c126bd3838b96c8d77200122d543af0001b1bd1da97ca1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K2VXUGNLT56WEDXBTV2GZ7AMQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not Every AI Problem is a Data Problem: We Should Be Intentional About Data Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Natasha Noy, Nino Scherrer, Tanya Rodchenko","submitted_at":"2025-01-23T15:58:14Z","abstract_excerpt":"While Large Language Models require more and more data to train and scale, rather than looking for any data to acquire, we should consider what types of tasks are more likely to benefit from data scaling. We should be intentional in our data acquisition. We argue that the shape of the data itself, such as its compositional and structural patterns, informs which tasks to prioritize in data scaling, and shapes the development of the next generation of compute paradigms for tasks where data scaling is inefficient, or even insufficient."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13779","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/2501.13779/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":"2026-07-05T11:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYCD/svUmYdeiuXT6Xzwle3eeo/SBV57U9Nsro01sKx78rmjSebXUyEQGd3ZtCC7W7+3Q5OwXaHPbvBVPRsRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:05:28.106235Z"},"content_sha256":"7ccc20f043c8c5987f7db123f7074ace002e2fea8cb1684482cbfd94f8929090","schema_version":"1.0","event_id":"sha256:7ccc20f043c8c5987f7db123f7074ace002e2fea8cb1684482cbfd94f8929090"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/bundle.json","state_url":"https://pith.science/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/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":"2026-08-11T11:05:28Z","links":{"resolver":"https://pith.science/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD","bundle":"https://pith.science/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/bundle.json","state":"https://pith.science/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2VXUGNLT56WEDXBTV2GZ7AMQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2VXUGNLT56WEDXBTV2GZ7AMQD","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":"110f6bc41a140e82b68c1b09b7d56154397e1503d03043268742f24d19105101","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T15:58:14Z","title_canon_sha256":"86f94a12140fb795297baefac68ce20b0a823332fe4e45046caf84a57d76db7c"},"schema_version":"1.0","source":{"id":"2501.13779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13779","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13779v2","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13779","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"K2VXUGNLT56W","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"K2VXUGNLT56WEDXB","created_at":"2026-07-05T11:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"K2VXUGNL","created_at":"2026-07-05T11:14:52Z"}],"graph_snapshots":[{"event_id":"sha256:7ccc20f043c8c5987f7db123f7074ace002e2fea8cb1684482cbfd94f8929090","target":"graph","created_at":"2026-07-05T11:14:52Z","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/2501.13779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models require more and more data to train and scale, rather than looking for any data to acquire, we should consider what types of tasks are more likely to benefit from data scaling. We should be intentional in our data acquisition. We argue that the shape of the data itself, such as its compositional and structural patterns, informs which tasks to prioritize in data scaling, and shapes the development of the next generation of compute paradigms for tasks where data scaling is inefficient, or even insufficient.","authors_text":"Natasha Noy, Nino Scherrer, Tanya Rodchenko","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T15:58:14Z","title":"Not Every AI Problem is a Data Problem: We Should Be Intentional About Data Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13779","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:f3437371cc0f65644c126bd3838b96c8d77200122d543af0001b1bd1da97ca1d","target":"record","created_at":"2026-07-05T11:14:52Z","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":"110f6bc41a140e82b68c1b09b7d56154397e1503d03043268742f24d19105101","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T15:58:14Z","title_canon_sha256":"86f94a12140fb795297baefac68ce20b0a823332fe4e45046caf84a57d76db7c"},"schema_version":"1.0","source":{"id":"2501.13779","kind":"arxiv","version":2}},"canonical_sha256":"56ab7a19ab9f7d620ee19d746cfc0c80e1bca2caf615e798afc10bf6a6f6d682","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56ab7a19ab9f7d620ee19d746cfc0c80e1bca2caf615e798afc10bf6a6f6d682","first_computed_at":"2026-07-05T11:14:52.824232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:52.824232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7R8oAVUVVRES7n9OVOwgJn3ZwyYly5tPjcHkSQbCWSCPwUZ6ZF68zCzh9B0j4VM94RARKJV0qCsmsifn65YwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:52.824640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3437371cc0f65644c126bd3838b96c8d77200122d543af0001b1bd1da97ca1d","sha256:7ccc20f043c8c5987f7db123f7074ace002e2fea8cb1684482cbfd94f8929090"],"state_sha256":"2b264d16bc98c926de240b36a909dcbbaaf8b41f97a1c739e56e70c67291f510"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDhw1jOEUrTNOYFSz5Alnjpw3AS5T5NJrshfPjXRvS7STO65IPe7o3HvC2rTKmvGdWPB3JOagQM18dyHrblGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:05:28.111042Z","bundle_sha256":"541654e4421c4f1be3f8d05699a605fee16337d44333826b9575f4acdcbb1d0c"}}