{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RHQZABO7J4B4YMRAGGJTDO7HKB","short_pith_number":"pith:RHQZABO7","canonical_record":{"source":{"id":"2603.07805","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-03-08T21:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"73bb1f3f284fc24858fc2156e14c16fd1b39acde1a083ae2c536d96df0f2471e","abstract_canon_sha256":"b23ea49a2c817e15d6081134656bfc6e09f58651eeefece56f652e08b1e1b68c"},"schema_version":"1.0"},"canonical_sha256":"89e19005df4f03cc3220319331bbe7506e7aadf4923c797671f25b7768c621d6","source":{"kind":"arxiv","id":"2603.07805","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07805","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07805v3","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07805","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"RHQZABO7J4B4","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"RHQZABO7J4B4YMRA","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"RHQZABO7","created_at":"2026-07-20T01:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RHQZABO7J4B4YMRAGGJTDO7HKB","target":"record","payload":{"canonical_record":{"source":{"id":"2603.07805","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-03-08T21:15:12Z","cross_cats_sorted":[],"title_canon_sha256":"73bb1f3f284fc24858fc2156e14c16fd1b39acde1a083ae2c536d96df0f2471e","abstract_canon_sha256":"b23ea49a2c817e15d6081134656bfc6e09f58651eeefece56f652e08b1e1b68c"},"schema_version":"1.0"},"canonical_sha256":"89e19005df4f03cc3220319331bbe7506e7aadf4923c797671f25b7768c621d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:18:28.557312Z","signature_b64":"D54jHPKXrqskWiUt9LSKMdFcPx/1Y7Xfbe1THObdFGeYt6QCNsrPyy3DewQywVhccm2OUB41voT/4bb/MmbPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e19005df4f03cc3220319331bbe7506e7aadf4923c797671f25b7768c621d6","last_reissued_at":"2026-07-20T01:18:28.556335Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:18:28.556335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.07805","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-20T01:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5mMYDRXn14vvGjzSLwQH9vhHR8N23UdkVIGw3oVV+EseLh+/VSeG+RV4ofMnrCg+MXJOrl706sbmibbTzLZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:44:43.759847Z"},"content_sha256":"36a64cf8615312753a275a181807ad503a20943428ed4a4bb237ee72abfdcab3","schema_version":"1.0","event_id":"sha256:36a64cf8615312753a275a181807ad503a20943428ed4a4bb237ee72abfdcab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RHQZABO7J4B4YMRAGGJTDO7HKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine Learning for Electrode Materials: Property Prediction via Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone.","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Arpit Mishra, Cameron Hargreaves, Gian-Marco Rignanese, Hao Wu","submitted_at":"2026-03-08T21:15:12Z","abstract_excerpt":"In this work, we benchmark three leading composition based Machine Learning (ML) frameworks, MODNet, CrabNet, and a random forest model based on Magpie features, predicting the properties of battery electrode materials using the Materials Project Battery Explorer dataset. We evaluate these models based on predictive accuracy, visualize numerical features using two-dimensional embeddings, and quantify performance using standard metrics. Our results demonstrate that CrabNet consistently outperforms the other models across all tests. To validate these findings, we employ bootstrap resampling and "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that CrabNet consistently outperforms the other models across all tests.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Materials Project Battery Explorer dataset and the chosen property labels accurately represent real electrode behavior without significant bias from data collection or labeling methods.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition, with cross-validation and clustering confirming coherent groupings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"24cd4224359e614af2bbc5812617ebcec72d84ba30de81d7274ba5bdc96e5674"},"source":{"id":"2603.07805","kind":"arxiv","version":3},"verdict":{"id":"c8b4ec29-f9e8-4339-a2a7-9031d3dcf793","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:12:14.770974Z","strongest_claim":"Our results demonstrate that CrabNet consistently outperforms the other models across all tests.","one_line_summary":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition, with cross-validation and clustering confirming coherent groupings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Materials Project Battery Explorer dataset and the chosen property labels accurately represent real electrode behavior without significant bias from data collection or labeling methods.","pith_extraction_headline":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.07805/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":2,"snapshot_sha256":"9ed38d58a3419056bb55442a8c58e0742b35c24dc5c0ca736793f86fc11fecbb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c8b4ec29-f9e8-4339-a2a7-9031d3dcf793"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-20T01:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uTW3mN0H3pgTiBTBgkhu4g4GXps2ReUqsW2UO9uAWNQRH9JKZWKHx4+cd15O6YFIEPfy95GmrV7wkodAABYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:44:43.760718Z"},"content_sha256":"1af41b9c5d69eb6c2aa0c8e0b9b5456701631e1334fe66ac116cd81efd0061e7","schema_version":"1.0","event_id":"sha256:1af41b9c5d69eb6c2aa0c8e0b9b5456701631e1334fe66ac116cd81efd0061e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/bundle.json","state_url":"https://pith.science/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/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":"2026-08-05T20:44:43Z","links":{"resolver":"https://pith.science/pith/RHQZABO7J4B4YMRAGGJTDO7HKB","bundle":"https://pith.science/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/bundle.json","state":"https://pith.science/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHQZABO7J4B4YMRAGGJTDO7HKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RHQZABO7J4B4YMRAGGJTDO7HKB","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":"b23ea49a2c817e15d6081134656bfc6e09f58651eeefece56f652e08b1e1b68c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-03-08T21:15:12Z","title_canon_sha256":"73bb1f3f284fc24858fc2156e14c16fd1b39acde1a083ae2c536d96df0f2471e"},"schema_version":"1.0","source":{"id":"2603.07805","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07805","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07805v3","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07805","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"RHQZABO7J4B4","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"RHQZABO7J4B4YMRA","created_at":"2026-07-20T01:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"RHQZABO7","created_at":"2026-07-20T01:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:1af41b9c5d69eb6c2aa0c8e0b9b5456701631e1334fe66ac116cd81efd0061e7","target":"graph","created_at":"2026-07-20T01:18:28Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our results demonstrate that CrabNet consistently outperforms the other models across all tests."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The Materials Project Battery Explorer dataset and the chosen property labels accurately represent real electrode behavior without significant bias from data collection or labeling methods."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition, with cross-validation and clustering confirming coherent groupings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone."}],"snapshot_sha256":"24cd4224359e614af2bbc5812617ebcec72d84ba30de81d7274ba5bdc96e5674"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9ed38d58a3419056bb55442a8c58e0742b35c24dc5c0ca736793f86fc11fecbb"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.07805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we benchmark three leading composition based Machine Learning (ML) frameworks, MODNet, CrabNet, and a random forest model based on Magpie features, predicting the properties of battery electrode materials using the Materials Project Battery Explorer dataset. We evaluate these models based on predictive accuracy, visualize numerical features using two-dimensional embeddings, and quantify performance using standard metrics. Our results demonstrate that CrabNet consistently outperforms the other models across all tests. To validate these findings, we employ bootstrap resampling and ","authors_text":"Arpit Mishra, Cameron Hargreaves, Gian-Marco Rignanese, Hao Wu","cross_cats":[],"headline":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-03-08T21:15:12Z","title":"Machine Learning for Electrode Materials: Property Prediction via Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07805","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T14:12:14.770974Z","id":"c8b4ec29-f9e8-4339-a2a7-9031d3dcf793","model_set":{"reader":"grok-4.3"},"one_line_summary":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition, with cross-validation and clustering confirming coherent groupings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CrabNet outperforms MODNet and random forest models when predicting battery electrode properties from composition alone.","strongest_claim":"Our results demonstrate that CrabNet consistently outperforms the other models across all tests.","weakest_assumption":"The Materials Project Battery Explorer dataset and the chosen property labels accurately represent real electrode behavior without significant bias from data collection or labeling methods."}},"verdict_id":"c8b4ec29-f9e8-4339-a2a7-9031d3dcf793"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36a64cf8615312753a275a181807ad503a20943428ed4a4bb237ee72abfdcab3","target":"record","created_at":"2026-07-20T01:18:28Z","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":"b23ea49a2c817e15d6081134656bfc6e09f58651eeefece56f652e08b1e1b68c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-03-08T21:15:12Z","title_canon_sha256":"73bb1f3f284fc24858fc2156e14c16fd1b39acde1a083ae2c536d96df0f2471e"},"schema_version":"1.0","source":{"id":"2603.07805","kind":"arxiv","version":3}},"canonical_sha256":"89e19005df4f03cc3220319331bbe7506e7aadf4923c797671f25b7768c621d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89e19005df4f03cc3220319331bbe7506e7aadf4923c797671f25b7768c621d6","first_computed_at":"2026-07-20T01:18:28.556335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:18:28.556335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D54jHPKXrqskWiUt9LSKMdFcPx/1Y7Xfbe1THObdFGeYt6QCNsrPyy3DewQywVhccm2OUB41voT/4bb/MmbPAw==","signature_status":"signed_v1","signed_at":"2026-07-20T01:18:28.557312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.07805","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36a64cf8615312753a275a181807ad503a20943428ed4a4bb237ee72abfdcab3","sha256:1af41b9c5d69eb6c2aa0c8e0b9b5456701631e1334fe66ac116cd81efd0061e7"],"state_sha256":"b7edf0d44b00e8c2fb69ee4158483af44d4d1782eabd6a7a78a09b2ea98b0cb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIbdHgBIUKKIyuUm8Oz/0rxG+NhMPlWbJ97QvSDuAWYMG+G0RuDFzgTD6USNXJziNIQsrPGF0nB2E4ERbWWrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:44:43.764876Z","bundle_sha256":"91a6e331d5a7411bc2447596363b07b10c0ac1f9980bde14d42bb0758f6cc45d"}}