{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4HQJD7RL7RHMEGT7Z4L327KABI","short_pith_number":"pith:4HQJD7RL","schema_version":"1.0","canonical_sha256":"e1e091fe2bfc4ec21a7fcf17bd7d400a170f806cc6796974f240108c45664617","source":{"kind":"arxiv","id":"2605.15691","version":1},"attestation_state":"computed","paper":{"title":"SEED: Targeted Data Selection by Weighted Independent Set","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Liu, Junwen Pan, Kuan Cheng, Kurt Keutzer, Lifeng Guo, Shanghang Zhang, Wenzhao Zheng, Yuan Zhang","submitted_at":"2026-05-15T07:26:54Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:26:54Z","cross_cats_sorted":[],"title_canon_sha256":"4f8c107d86aab9ba5416af4fd322999935b71226d4944e301648b628d1553096","abstract_canon_sha256":"b70170db178442fe74117ea37e6eed436f84148a0d8005da6e75fe60a802bd6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:12.743627Z","signature_b64":"21B8m+kJS+33XOg3S6rGSMVqs18jRB9QhwPg3eRZIPzMSZ36kx9TX+CgUrCdpRJW03so8V16y4sI4zW99yzmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1e091fe2bfc4ec21a7fcf17bd7d400a170f806cc6796974f240108c45664617","last_reissued_at":"2026-05-20T00:01:12.742877Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:12.742877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEED: Targeted Data Selection by Weighted Independent Set","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Liu, Junwen Pan, Kuan Cheng, Kurt Keutzer, Lifeng Guo, Shanghang Zhang, Wenzhao Zheng, Yuan Zhang","submitted_at":"2026-05-15T07:26:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15691","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/2605.15691/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"3af710fa809551cfedf4bb63dd70c9d4ed0999615d91373af4a363d623231052"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15691","created_at":"2026-05-20T00:01:12.742985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15691v1","created_at":"2026-05-20T00:01:12.742985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15691","created_at":"2026-05-20T00:01:12.742985+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HQJD7RL7RHM","created_at":"2026-05-20T00:01:12.742985+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HQJD7RL7RHMEGT7","created_at":"2026-05-20T00:01:12.742985+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HQJD7RL","created_at":"2026-05-20T00:01:12.742985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI","json":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI.json","graph_json":"https://pith.science/api/pith-number/4HQJD7RL7RHMEGT7Z4L327KABI/graph.json","events_json":"https://pith.science/api/pith-number/4HQJD7RL7RHMEGT7Z4L327KABI/events.json","paper":"https://pith.science/paper/4HQJD7RL"},"agent_actions":{"view_html":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI","download_json":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI.json","view_paper":"https://pith.science/paper/4HQJD7RL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15691&json=true","fetch_graph":"https://pith.science/api/pith-number/4HQJD7RL7RHMEGT7Z4L327KABI/graph.json","fetch_events":"https://pith.science/api/pith-number/4HQJD7RL7RHMEGT7Z4L327KABI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI/action/storage_attestation","attest_author":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI/action/author_attestation","sign_citation":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI/action/citation_signature","submit_replication":"https://pith.science/pith/4HQJD7RL7RHMEGT7Z4L327KABI/action/replication_record"}},"created_at":"2026-05-20T00:01:12.742985+00:00","updated_at":"2026-05-20T00:01:12.742985+00:00"}