{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2532QVHK4K6FOKZI2NZH72YX42","short_pith_number":"pith:2532QVHK","canonical_record":{"source":{"id":"2605.24779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T23:43:24Z","cross_cats_sorted":["cs.AI","math.CO"],"title_canon_sha256":"99046114adf3613c013fb7c2619579aab0368a67e037e02ae1f1ea6ca445c89e","abstract_canon_sha256":"3030d9dcb356484064704191ffda931ca67b845d0b50511f6bc6dbae54b733a5"},"schema_version":"1.0"},"canonical_sha256":"d777a854eae2bc572b28d3727feb17e69d43a9e0b13b4d9d25258b1dcf45b2c7","source":{"kind":"arxiv","id":"2605.24779","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24779","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24779v1","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24779","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_12","alias_value":"2532QVHK4K6F","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_16","alias_value":"2532QVHK4K6FOKZI","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_8","alias_value":"2532QVHK","created_at":"2026-05-26T01:03:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2532QVHK4K6FOKZI2NZH72YX42","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T23:43:24Z","cross_cats_sorted":["cs.AI","math.CO"],"title_canon_sha256":"99046114adf3613c013fb7c2619579aab0368a67e037e02ae1f1ea6ca445c89e","abstract_canon_sha256":"3030d9dcb356484064704191ffda931ca67b845d0b50511f6bc6dbae54b733a5"},"schema_version":"1.0"},"canonical_sha256":"d777a854eae2bc572b28d3727feb17e69d43a9e0b13b4d9d25258b1dcf45b2c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:57.747055Z","signature_b64":"9LXQ3jYuP2Vq/G/UtPFGwLfFuprSS4M2f09OMVe4KO4gSnLtFRLKfE8A73ZIZYY4ibUmqbHHux5UAIxz2nA/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d777a854eae2bc572b28d3727feb17e69d43a9e0b13b4d9d25258b1dcf45b2c7","last_reissued_at":"2026-05-26T01:03:57.746247Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:57.746247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24779","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":"2026-05-26T01:03:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSRMzahEKDHREY5RUVx9ZUpkBUIjc53+mcWxbiUWnDTiAcyOd8/1YCHF86cSlOHCT0TJhpgf0gn8fsqZXkyqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T16:53:33.279128Z"},"content_sha256":"0e64738bc6125ed06615f416936a7a3fece1cf029da2c5e311d23a16c4b9ed39","schema_version":"1.0","event_id":"sha256:0e64738bc6125ed06615f416936a7a3fece1cf029da2c5e311d23a16c4b9ed39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2532QVHK4K6FOKZI2NZH72YX42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Complement Submodular Information Measures for Balanced and Robust Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.CO"],"primary_cat":"cs.LG","authors_text":"Rishabh Iyer","submitted_at":"2026-05-23T23:43:24Z","abstract_excerpt":"Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability to model coverage, diversity, and representativeness. However, classical submodular objectives optimize only the selected subset and do not explicitly preserve structural information between the selected subset and the remaining data. In many modern machine learning applications, including train/validation/test splitting, benchmark construction, and robust subset selection, the quality of a selection depends critically on preserving balanced str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24779","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/2605.24779/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":"2026-05-26T01:03:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/SkXYhmzAFevZOQuLs5DQstwhWS3h4clnj24vAYlWqyrcaC34l3v7wSQ67UKHBauox17EPJkwnzvjx+rhcYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T16:53:33.279527Z"},"content_sha256":"a5b2df19c8659bfb269d47c90ec3574088e7a74a9f969d2dba082845b9bee5e8","schema_version":"1.0","event_id":"sha256:a5b2df19c8659bfb269d47c90ec3574088e7a74a9f969d2dba082845b9bee5e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2532QVHK4K6FOKZI2NZH72YX42/bundle.json","state_url":"https://pith.science/pith/2532QVHK4K6FOKZI2NZH72YX42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2532QVHK4K6FOKZI2NZH72YX42/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":"2026-07-02T16:53:33Z","links":{"resolver":"https://pith.science/pith/2532QVHK4K6FOKZI2NZH72YX42","bundle":"https://pith.science/pith/2532QVHK4K6FOKZI2NZH72YX42/bundle.json","state":"https://pith.science/pith/2532QVHK4K6FOKZI2NZH72YX42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2532QVHK4K6FOKZI2NZH72YX42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2532QVHK4K6FOKZI2NZH72YX42","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":"3030d9dcb356484064704191ffda931ca67b845d0b50511f6bc6dbae54b733a5","cross_cats_sorted":["cs.AI","math.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T23:43:24Z","title_canon_sha256":"99046114adf3613c013fb7c2619579aab0368a67e037e02ae1f1ea6ca445c89e"},"schema_version":"1.0","source":{"id":"2605.24779","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24779","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24779v1","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24779","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_12","alias_value":"2532QVHK4K6F","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_16","alias_value":"2532QVHK4K6FOKZI","created_at":"2026-05-26T01:03:57Z"},{"alias_kind":"pith_short_8","alias_value":"2532QVHK","created_at":"2026-05-26T01:03:57Z"}],"graph_snapshots":[{"event_id":"sha256:a5b2df19c8659bfb269d47c90ec3574088e7a74a9f969d2dba082845b9bee5e8","target":"graph","created_at":"2026-05-26T01:03:57Z","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/2605.24779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability to model coverage, diversity, and representativeness. However, classical submodular objectives optimize only the selected subset and do not explicitly preserve structural information between the selected subset and the remaining data. In many modern machine learning applications, including train/validation/test splitting, benchmark construction, and robust subset selection, the quality of a selection depends critically on preserving balanced str","authors_text":"Rishabh Iyer","cross_cats":["cs.AI","math.CO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T23:43:24Z","title":"Complement Submodular Information Measures for Balanced and Robust Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24779","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":"sha256:0e64738bc6125ed06615f416936a7a3fece1cf029da2c5e311d23a16c4b9ed39","target":"record","created_at":"2026-05-26T01:03:57Z","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":"3030d9dcb356484064704191ffda931ca67b845d0b50511f6bc6dbae54b733a5","cross_cats_sorted":["cs.AI","math.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T23:43:24Z","title_canon_sha256":"99046114adf3613c013fb7c2619579aab0368a67e037e02ae1f1ea6ca445c89e"},"schema_version":"1.0","source":{"id":"2605.24779","kind":"arxiv","version":1}},"canonical_sha256":"d777a854eae2bc572b28d3727feb17e69d43a9e0b13b4d9d25258b1dcf45b2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d777a854eae2bc572b28d3727feb17e69d43a9e0b13b4d9d25258b1dcf45b2c7","first_computed_at":"2026-05-26T01:03:57.746247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:57.746247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9LXQ3jYuP2Vq/G/UtPFGwLfFuprSS4M2f09OMVe4KO4gSnLtFRLKfE8A73ZIZYY4ibUmqbHHux5UAIxz2nA/DQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:57.747055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24779","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e64738bc6125ed06615f416936a7a3fece1cf029da2c5e311d23a16c4b9ed39","sha256:a5b2df19c8659bfb269d47c90ec3574088e7a74a9f969d2dba082845b9bee5e8"],"state_sha256":"5ca4e2d66e15767f42a4ba4e09a23d7b3d245be113427b11c064f6165fbf49f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73lBAPNgrzUiIbfLcDEx4uTQ5nO7H+0FLowQffQJaz7Lt+PcKeF9sHrRxvutQJWTCc2qn/7LNpwrVp+jdWpcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T16:53:33.281924Z","bundle_sha256":"ea53777a0bd6ea5d24d35a57a5d9666088d5f9db9a019725f867f434b566f149"}}