{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HU4V53SJWQ43PVSPFUTHFPPOSK","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":"bd32cac4297b406f226af7c9155862ecff4407dfacf543313354da5d8d57c7c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:36:24Z","title_canon_sha256":"c99dd1e4950d55bf5e289afa396555f6848844afd15381ba0340854b7ca51f2d"},"schema_version":"1.0","source":{"id":"2605.23969","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23969","created_at":"2026-05-26T00:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23969v1","created_at":"2026-05-26T00:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23969","created_at":"2026-05-26T00:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"HU4V53SJWQ43","created_at":"2026-05-26T00:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"HU4V53SJWQ43PVSP","created_at":"2026-05-26T00:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"HU4V53SJ","created_at":"2026-05-26T00:02:24Z"}],"graph_snapshots":[{"event_id":"sha256:ca204b81878a6f1f6fa458b04ddfda1d76e17c2b893f48a65f2fa98d23cffce2","target":"graph","created_at":"2026-05-26T00:02:24Z","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/2605.23969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying useful data and efficiently fine-tuning. High-quality and diverse pruned data can help models achieve lossless performance at a lower cost. In this paper, we propose \\textbf{SLAP}, a novel batch-aware data selection framework that evaluates the learnability of entire batch compositions rather than individual. SLAP ensures comprehensive data distribution coverage","authors_text":"Hao Chen, Jianhang Ding, Renshu Gu, Run Zou, Wen Wu, Yifan Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:36:24Z","title":"SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23969","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:dddf0f75fc380b10440bb8aef73a12fc4aea61cefda71ae779534216b5bc8aa7","target":"record","created_at":"2026-05-26T00:02:24Z","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":"bd32cac4297b406f226af7c9155862ecff4407dfacf543313354da5d8d57c7c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:36:24Z","title_canon_sha256":"c99dd1e4950d55bf5e289afa396555f6848844afd15381ba0340854b7ca51f2d"},"schema_version":"1.0","source":{"id":"2605.23969","kind":"arxiv","version":1}},"canonical_sha256":"3d395eee49b439b7d64f2d2672bdee92abb09bdf839c596b7a0fe77ab745866e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d395eee49b439b7d64f2d2672bdee92abb09bdf839c596b7a0fe77ab745866e","first_computed_at":"2026-05-26T00:02:24.464607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T00:02:24.464607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yh6QltY8Z9jFVaW1uay/Re67K8cZUaanjns5YGyJNENEFM6ya8CqTR8gG49RlJCUVtGFmtyk2G/rB5rjmVu8Dg==","signature_status":"signed_v1","signed_at":"2026-05-26T00:02:24.465422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23969","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dddf0f75fc380b10440bb8aef73a12fc4aea61cefda71ae779534216b5bc8aa7","sha256:ca204b81878a6f1f6fa458b04ddfda1d76e17c2b893f48a65f2fa98d23cffce2"],"state_sha256":"cac582db6239e59ff28cd516cb07b327e701e990c0b8628933de112447fb9db1"}