{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7DN7K4656HVQ7N4ADF7M7Q24PN","short_pith_number":"pith:7DN7K465","schema_version":"1.0","canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","source":{"kind":"arxiv","id":"2405.11404","version":1},"attestation_state":"computed","paper":{"title":"How big is Big Data?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"primary_cat":"stat.ML","authors_text":"Claudia Draxl, Daniel T. Speckhard, Luca M. Ghiringhelli, Martin Kuban, Santiago Rigamonti, Tim Bechtel","submitted_at":"2024-05-18T22:13:55Z","abstract_excerpt":"Big data has ushered in a new wave of predictive power using machine learning models. In this work, we assess what {\\it big} means in the context of typical materials-science machine-learning problems. This concerns not only data volume, but also data quality and veracity as much as infrastructure issues. With selected examples, we ask (i) how models generalize to similar datasets, (ii) how high-quality datasets can be gathered from heterogenous sources, (iii) how the feature set and complexity of a model can affect expressivity, and (iv) what infrastructure requirements are needed to create l"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.11404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-18T22:13:55Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"title_canon_sha256":"8e6604f498684e1add2cd13c384f01567bb00e0b4ee3416b104a61c3b59186cf","abstract_canon_sha256":"341cd89a435867d0df31566bc0f1c0afc03c1c4a9835e44b2428e47252cccb1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:38.870906Z","signature_b64":"HeLG/+tyrKJIhXA+SiqM1m/R4IuLEmVqZgAoW+VXDBDnvwwTjyjspdJwm5o9VTSeOCiu4bovCAieQB78DCv9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","last_reissued_at":"2026-07-05T08:20:38.870341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:38.870341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How big is Big Data?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"primary_cat":"stat.ML","authors_text":"Claudia Draxl, Daniel T. Speckhard, Luca M. Ghiringhelli, Martin Kuban, Santiago Rigamonti, Tim Bechtel","submitted_at":"2024-05-18T22:13:55Z","abstract_excerpt":"Big data has ushered in a new wave of predictive power using machine learning models. In this work, we assess what {\\it big} means in the context of typical materials-science machine-learning problems. This concerns not only data volume, but also data quality and veracity as much as infrastructure issues. With selected examples, we ask (i) how models generalize to similar datasets, (ii) how high-quality datasets can be gathered from heterogenous sources, (iii) how the feature set and complexity of a model can affect expressivity, and (iv) what infrastructure requirements are needed to create l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11404","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/2405.11404/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.11404","created_at":"2026-07-05T08:20:38.870407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11404v1","created_at":"2026-07-05T08:20:38.870407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11404","created_at":"2026-07-05T08:20:38.870407+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DN7K4656HVQ","created_at":"2026-07-05T08:20:38.870407+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DN7K4656HVQ7N4A","created_at":"2026-07-05T08:20:38.870407+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DN7K465","created_at":"2026-07-05T08:20:38.870407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN","json":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN.json","graph_json":"https://pith.science/api/pith-number/7DN7K4656HVQ7N4ADF7M7Q24PN/graph.json","events_json":"https://pith.science/api/pith-number/7DN7K4656HVQ7N4ADF7M7Q24PN/events.json","paper":"https://pith.science/paper/7DN7K465"},"agent_actions":{"view_html":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN","download_json":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN.json","view_paper":"https://pith.science/paper/7DN7K465","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11404&json=true","fetch_graph":"https://pith.science/api/pith-number/7DN7K4656HVQ7N4ADF7M7Q24PN/graph.json","fetch_events":"https://pith.science/api/pith-number/7DN7K4656HVQ7N4ADF7M7Q24PN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/action/storage_attestation","attest_author":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/action/author_attestation","sign_citation":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/action/citation_signature","submit_replication":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/action/replication_record"}},"created_at":"2026-07-05T08:20:38.870407+00:00","updated_at":"2026-07-05T08:20:38.870407+00:00"}