{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WXOUUBNMSXYGZ62MSRS6NJ7TY7","short_pith_number":"pith:WXOUUBNM","canonical_record":{"source":{"id":"2507.10904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T01:43:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b45a03ad7b7e208c6b8ea94cf754d87a51a1b11254b450884ac7ac49869114","abstract_canon_sha256":"252f5683c21b84619e35330da23e934c012e98d281831655c975500fbbb43e9f"},"schema_version":"1.0"},"canonical_sha256":"b5dd4a05ac95f06cfb4c9465e6a7f3c7c6e886b9363dc38aa2f208ce13c6832c","source":{"kind":"arxiv","id":"2507.10904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10904","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10904v2","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10904","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"WXOUUBNMSXYG","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"WXOUUBNMSXYGZ62M","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"WXOUUBNM","created_at":"2026-07-05T11:53:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WXOUUBNMSXYGZ62MSRS6NJ7TY7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T01:43:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b45a03ad7b7e208c6b8ea94cf754d87a51a1b11254b450884ac7ac49869114","abstract_canon_sha256":"252f5683c21b84619e35330da23e934c012e98d281831655c975500fbbb43e9f"},"schema_version":"1.0"},"canonical_sha256":"b5dd4a05ac95f06cfb4c9465e6a7f3c7c6e886b9363dc38aa2f208ce13c6832c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:28.045863Z","signature_b64":"AIWlP4Y5WgeOrM3nnUL2OueZK2tn7VYBqo9yM4iDhlZKZeJ9TZm0uhQQZSDnCPvn0B+mOeu/gHxIyO/lSI5JDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5dd4a05ac95f06cfb4c9465e6a7f3c7c6e886b9363dc38aa2f208ce13c6832c","last_reissued_at":"2026-07-05T11:53:28.043068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:28.043068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10904","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":"2026-07-05T11:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFBvkKVp4h0yohFOSIzkrVOILHXl5Ta9tSFw1hfoJ3PV6yCXE6OFVzfi70WcgjXLqLesjU5sdInEm6OoF4/qAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:50:46.533357Z"},"content_sha256":"4c06969a4642d971aeac886f30e942d097ab6b9a3d34de68d24b23440ee867ec","schema_version":"1.0","event_id":"sha256:4c06969a4642d971aeac886f30e942d097ab6b9a3d34de68d24b23440ee867ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WXOUUBNMSXYGZ62MSRS6NJ7TY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Class-Proportional Coreset Selection for Difficulty-Separable Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Atul Prakash, Elisa Tsai, Haizhong Zheng","submitted_at":"2025-07-15T01:43:32Z","abstract_excerpt":"High-quality training data is essential for building reliable and efficient machine learning systems. One-shot coreset selection addresses this by pruning the dataset while maintaining or even improving model performance, often relying on training-dynamics-based data difficulty scores. However, most existing methods implicitly assume class-wise homogeneity in data difficulty, overlooking variation in data difficulty across different classes. In this work, we challenge this assumption by showing that, in domains such as network intrusion detection and medical imaging, data difficulty often clus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10904","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/2507.10904/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":"2026-07-05T11:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WM252s6/8dc5pnU8uHDr8wfDGUuvsorw1XYKWhfIrGH4UvqUquNW5r2C0gvmQ/OPszYbQOC2EidIDxuTMYWICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:50:46.533858Z"},"content_sha256":"c3d40ad301a61ae1d5f56064ad4687db2ec2d91cf8610e599e4bb3c53a56c743","schema_version":"1.0","event_id":"sha256:c3d40ad301a61ae1d5f56064ad4687db2ec2d91cf8610e599e4bb3c53a56c743"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/bundle.json","state_url":"https://pith.science/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/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":"2026-08-08T02:50:46Z","links":{"resolver":"https://pith.science/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7","bundle":"https://pith.science/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/bundle.json","state":"https://pith.science/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXOUUBNMSXYGZ62MSRS6NJ7TY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WXOUUBNMSXYGZ62MSRS6NJ7TY7","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":"252f5683c21b84619e35330da23e934c012e98d281831655c975500fbbb43e9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T01:43:32Z","title_canon_sha256":"84b45a03ad7b7e208c6b8ea94cf754d87a51a1b11254b450884ac7ac49869114"},"schema_version":"1.0","source":{"id":"2507.10904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10904","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10904v2","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10904","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"WXOUUBNMSXYG","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"WXOUUBNMSXYGZ62M","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"WXOUUBNM","created_at":"2026-07-05T11:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:c3d40ad301a61ae1d5f56064ad4687db2ec2d91cf8610e599e4bb3c53a56c743","target":"graph","created_at":"2026-07-05T11:53:28Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.10904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality training data is essential for building reliable and efficient machine learning systems. One-shot coreset selection addresses this by pruning the dataset while maintaining or even improving model performance, often relying on training-dynamics-based data difficulty scores. However, most existing methods implicitly assume class-wise homogeneity in data difficulty, overlooking variation in data difficulty across different classes. In this work, we challenge this assumption by showing that, in domains such as network intrusion detection and medical imaging, data difficulty often clus","authors_text":"Atul Prakash, Elisa Tsai, Haizhong Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T01:43:32Z","title":"Class-Proportional Coreset Selection for Difficulty-Separable Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10904","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":"sha256:4c06969a4642d971aeac886f30e942d097ab6b9a3d34de68d24b23440ee867ec","target":"record","created_at":"2026-07-05T11:53:28Z","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":"252f5683c21b84619e35330da23e934c012e98d281831655c975500fbbb43e9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T01:43:32Z","title_canon_sha256":"84b45a03ad7b7e208c6b8ea94cf754d87a51a1b11254b450884ac7ac49869114"},"schema_version":"1.0","source":{"id":"2507.10904","kind":"arxiv","version":2}},"canonical_sha256":"b5dd4a05ac95f06cfb4c9465e6a7f3c7c6e886b9363dc38aa2f208ce13c6832c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5dd4a05ac95f06cfb4c9465e6a7f3c7c6e886b9363dc38aa2f208ce13c6832c","first_computed_at":"2026-07-05T11:53:28.043068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:28.043068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AIWlP4Y5WgeOrM3nnUL2OueZK2tn7VYBqo9yM4iDhlZKZeJ9TZm0uhQQZSDnCPvn0B+mOeu/gHxIyO/lSI5JDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:28.045863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c06969a4642d971aeac886f30e942d097ab6b9a3d34de68d24b23440ee867ec","sha256:c3d40ad301a61ae1d5f56064ad4687db2ec2d91cf8610e599e4bb3c53a56c743"],"state_sha256":"ef19532989bce3046da4b98ee094736a32e36dd2ff63d84ed29e3a3d1ec8f07d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14CYM5laRypgHflvfytEqFo6xl9lvaiHTr6308Ug7NyM34i8ATwzoJWYedPrv2KL4mzTIfs2cRrm6AKnjwn0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:50:46.537528Z","bundle_sha256":"98a1fe0ace2d6e0f95ae81d8ca0201c6235667dedda12c342400edfd6e612915"}}