{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OSOH2Y6XCJJYBZMCWXUH2EZKLC","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":"e388755fd9a84defedbad26c4244e2203fcac8f5e81b8112abb4e0f7800d0eda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T20:53:37Z","title_canon_sha256":"a1af830a7243306fb4736d3df7f78a7d94497a98fd9cd54a84f70696f1e78994"},"schema_version":"1.0","source":{"id":"2508.08466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08466","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08466v1","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08466","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"OSOH2Y6XCJJY","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"OSOH2Y6XCJJYBZMC","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"OSOH2Y6X","created_at":"2026-07-05T11:52:29Z"}],"graph_snapshots":[{"event_id":"sha256:717a693588f59ebf34ee63c34dd2376d88201789f8b8acf16cdf6ed778587123","target":"graph","created_at":"2026-07-05T11:52:29Z","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/2508.08466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small large language models (LLMs) often face difficulties in aligning output to human preferences, particularly when operating under severe performance gaps. In this work, we propose two lightweight DPO-based variants -- Adaptive Margin-Sigmoid Loss and APO-hinge-zero -- to better address underperformance scenarios by introducing margin-based objectives and selective update mechanisms.\n  Our APO-hinge-zero method, which combines hinge-induced hard-example mining with the chosen-focused optimization of APO-zero, achieves strong results. In AlpacaEval, APO-hinge-zero improves the win rate by +2","authors_text":"Daren Yao, Jinsong Yuan, Ruike Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T20:53:37Z","title":"Enhancing Small LLM Alignment through Margin-Based Objective Modifications under Resource Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08466","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:a64f53fcfa929b2b8c5d0e0aec30095b9e5909f635ab19350658316ff44b80b4","target":"record","created_at":"2026-07-05T11:52:29Z","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":"e388755fd9a84defedbad26c4244e2203fcac8f5e81b8112abb4e0f7800d0eda","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T20:53:37Z","title_canon_sha256":"a1af830a7243306fb4736d3df7f78a7d94497a98fd9cd54a84f70696f1e78994"},"schema_version":"1.0","source":{"id":"2508.08466","kind":"arxiv","version":1}},"canonical_sha256":"749c7d63d7125380e582b5e87d132a588ca32888e4acf8b4a10de0ba4a520f8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"749c7d63d7125380e582b5e87d132a588ca32888e4acf8b4a10de0ba4a520f8e","first_computed_at":"2026-07-05T11:52:29.021765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:29.021765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GgiFJXtcXgMASC1G3IZojx+ix0E56ady9T69KoM88k7x6p5Jg9N2tF4NOKuOM4sGUDm7XmqvXv4Z1N7Q1nCtAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:29.022311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a64f53fcfa929b2b8c5d0e0aec30095b9e5909f635ab19350658316ff44b80b4","sha256:717a693588f59ebf34ee63c34dd2376d88201789f8b8acf16cdf6ed778587123"],"state_sha256":"e1df22407852b2a15e283b7fbbd0ce04215b1e657bd968b789f31980e1235ef2"}