{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4HQJD7RL7RHMEGT7Z4L327KABI","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":"b70170db178442fe74117ea37e6eed436f84148a0d8005da6e75fe60a802bd6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:26:54Z","title_canon_sha256":"4f8c107d86aab9ba5416af4fd322999935b71226d4944e301648b628d1553096"},"schema_version":"1.0","source":{"id":"2605.15691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15691","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15691v1","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15691","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"4HQJD7RL7RHM","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"4HQJD7RL7RHMEGT7","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"4HQJD7RL","created_at":"2026-05-20T00:01:12Z"}],"graph_snapshots":[{"event_id":"sha256:8a64374e18fa427d8b4a8c615490167a011e827cf85b0ed6b4e4b638674c6c8c","target":"graph","created_at":"2026-05-20T00:01:12Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:29.221862Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.041411Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15691/integrity.json","findings":[],"snapshot_sha256":"3af710fa809551cfedf4bb63dd70c9d4ed0999615d91373af4a363d623231052","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph, where nodes represent data samples weighted by influence, and edges connect semantically redundant pairs. This formulation naturally yields subsets that are simultaneously high-quality and diverse. However, two challenges arise in practice: naive node weights fail to distinguish informative signals from gradient noise, and edge construction under heterogene","authors_text":"Chang Liu, Junwen Pan, Kuan Cheng, Kurt Keutzer, Lifeng Guo, Shanghang Zhang, Wenzhao Zheng, Yuan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:26:54Z","title":"SEED: Targeted Data Selection by Weighted Independent Set"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15691","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":"sha256:1ba37aae2f71b51ad78a45610835f243e642543e1f8d92831cb42a51b07c7f5e","target":"record","created_at":"2026-05-20T00:01:12Z","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":"b70170db178442fe74117ea37e6eed436f84148a0d8005da6e75fe60a802bd6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:26:54Z","title_canon_sha256":"4f8c107d86aab9ba5416af4fd322999935b71226d4944e301648b628d1553096"},"schema_version":"1.0","source":{"id":"2605.15691","kind":"arxiv","version":1}},"canonical_sha256":"e1e091fe2bfc4ec21a7fcf17bd7d400a170f806cc6796974f240108c45664617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1e091fe2bfc4ec21a7fcf17bd7d400a170f806cc6796974f240108c45664617","first_computed_at":"2026-05-20T00:01:12.742877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:12.742877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"21B8m+kJS+33XOg3S6rGSMVqs18jRB9QhwPg3eRZIPzMSZ36kx9TX+CgUrCdpRJW03so8V16y4sI4zW99yzmCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:12.743627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ba37aae2f71b51ad78a45610835f243e642543e1f8d92831cb42a51b07c7f5e","sha256:8a64374e18fa427d8b4a8c615490167a011e827cf85b0ed6b4e4b638674c6c8c"],"state_sha256":"e62ea6a0a959bdbb6ee2aa45582657b3ba9f9f7f25462d170efdc84f822ff8fa"}