{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7DN7K4656HVQ7N4ADF7M7Q24PN","short_pith_number":"pith:7DN7K465","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"},"canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","source":{"kind":"arxiv","id":"2405.11404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11404","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11404v1","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11404","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"7DN7K4656HVQ","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"7DN7K4656HVQ7N4A","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"7DN7K465","created_at":"2026-07-05T08:20:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7DN7K4656HVQ7N4ADF7M7Q24PN","target":"record","payload":{"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"},"canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","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"},"source_kind":"arxiv","source_id":"2405.11404","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":"2026-07-05T08:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5T0WQatSQlrQic5DLfDbUZbg8ln7m5FZve/41h3qDRilsXF0EovlqTRlj8Atg/VEvqX3jzfReaImi4j2h6YCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:22:41.767706Z"},"content_sha256":"409fd7166989c384206c21f05a3b2758b2dbb05c23bc53f85de7d3f5493e5168","schema_version":"1.0","event_id":"sha256:409fd7166989c384206c21f05a3b2758b2dbb05c23bc53f85de7d3f5493e5168"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7DN7K4656HVQ7N4ADF7M7Q24PN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xhbd5je8GJxhJzdhxM8UE3+RS6DJLnUV7lzymIdjIp//DrFIUu0YLwrCUSB4A+eno5yO4JmKEHvoWsDkieZlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:22:41.768090Z"},"content_sha256":"2cd81de7ecf098e0dc0d2ff4a66834cb1b99af61b29041f8f558e613d328b5a9","schema_version":"1.0","event_id":"sha256:2cd81de7ecf098e0dc0d2ff4a66834cb1b99af61b29041f8f558e613d328b5a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/bundle.json","state_url":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/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":"2026-07-07T03:22:41Z","links":{"resolver":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN","bundle":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/bundle.json","state":"https://pith.science/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DN7K4656HVQ7N4ADF7M7Q24PN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7DN7K4656HVQ7N4ADF7M7Q24PN","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":"341cd89a435867d0df31566bc0f1c0afc03c1c4a9835e44b2428e47252cccb1c","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-18T22:13:55Z","title_canon_sha256":"8e6604f498684e1add2cd13c384f01567bb00e0b4ee3416b104a61c3b59186cf"},"schema_version":"1.0","source":{"id":"2405.11404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11404","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11404v1","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11404","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"7DN7K4656HVQ","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"7DN7K4656HVQ7N4A","created_at":"2026-07-05T08:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"7DN7K465","created_at":"2026-07-05T08:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:2cd81de7ecf098e0dc0d2ff4a66834cb1b99af61b29041f8f558e613d328b5a9","target":"graph","created_at":"2026-07-05T08:20:38Z","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/2405.11404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Claudia Draxl, Daniel T. Speckhard, Luca M. Ghiringhelli, Martin Kuban, Santiago Rigamonti, Tim Bechtel","cross_cats":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-18T22:13:55Z","title":"How big is Big Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11404","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":"sha256:409fd7166989c384206c21f05a3b2758b2dbb05c23bc53f85de7d3f5493e5168","target":"record","created_at":"2026-07-05T08:20:38Z","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":"341cd89a435867d0df31566bc0f1c0afc03c1c4a9835e44b2428e47252cccb1c","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-18T22:13:55Z","title_canon_sha256":"8e6604f498684e1add2cd13c384f01567bb00e0b4ee3416b104a61c3b59186cf"},"schema_version":"1.0","source":{"id":"2405.11404","kind":"arxiv","version":1}},"canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8dbf573ddf1eb0fb780197ecfc35c7b794c98afb037f7840e47b8428aa2fdee","first_computed_at":"2026-07-05T08:20:38.870341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:38.870341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HeLG/+tyrKJIhXA+SiqM1m/R4IuLEmVqZgAoW+VXDBDnvwwTjyjspdJwm5o9VTSeOCiu4bovCAieQB78DCv9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:38.870906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:409fd7166989c384206c21f05a3b2758b2dbb05c23bc53f85de7d3f5493e5168","sha256:2cd81de7ecf098e0dc0d2ff4a66834cb1b99af61b29041f8f558e613d328b5a9"],"state_sha256":"f5ff439d981dae1fdaa8a65d45e9524ca4759739773cdc33e543ae430840b0b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMmtXHWmCRdlNi+cNDmQMcu0oChT6kSWC4EalqFwbWQxfkirsrmgw44s4j9TJ9a7ectXJymcWDpxFERE8OyPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:22:41.770284Z","bundle_sha256":"b372e1e71bf539a43d3148e0da713280fcbdce36e92fc8c9f1968a6600c3db35"}}