{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5RGIQLQLZE7GR4HSQX7DY53FAY","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":"02d8c422788bde74175ca644a1d35a4e862749ec46c353b26f8051e24e004d17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T04:34:39Z","title_canon_sha256":"0c59010e21c1094cbcbd174241208f4afe6557a9ab4fb2c2bd13acc5acd73518"},"schema_version":"1.0","source":{"id":"2407.06542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06542","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06542v2","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06542","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"5RGIQLQLZE7G","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"5RGIQLQLZE7GR4HS","created_at":"2026-07-05T09:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"5RGIQLQL","created_at":"2026-07-05T09:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:94abdb2edda16cb148547e0b67c9a9bdbf2511035be145e638d7cc05e5c354d3","target":"graph","created_at":"2026-07-05T09:14:54Z","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/2407.06542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies measuring the impact of various design choices throughout the whole training process. We first conduct a rigorous analysis over a three-stage training pipeline consisting of supervised fine-tuning, offline preference learning, and online preference learning. We have found that using techniques like sequence packing, loss masking in SFT, increasing the prefer","authors_text":"Qingyang Wu, Xiao Yu, Yu Li, Zhou Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T04:34:39Z","title":"LIONs: An Empirically Optimized Approach to Align Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06542","kind":"arxiv","version":2},"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":"sha256:2be3fe29d88298fedb19b347db50ddb2de4fb7587688f38eeeb6fa7927d53aac","target":"record","created_at":"2026-07-05T09:14:54Z","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":"02d8c422788bde74175ca644a1d35a4e862749ec46c353b26f8051e24e004d17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T04:34:39Z","title_canon_sha256":"0c59010e21c1094cbcbd174241208f4afe6557a9ab4fb2c2bd13acc5acd73518"},"schema_version":"1.0","source":{"id":"2407.06542","kind":"arxiv","version":2}},"canonical_sha256":"ec4c882e0bc93e68f0f285fe3c7765060db46a1b5bed553312f31246cd3e3236","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4c882e0bc93e68f0f285fe3c7765060db46a1b5bed553312f31246cd3e3236","first_computed_at":"2026-07-05T09:14:54.850408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:54.850408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KsKCUTuBOjk4nY7K1OqDVG7yYsbGHCUtuXbsDwLrzSYpW/J8LRY7POJfS/Rho3h8QUUKg+kr0W6StzO2cKoRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:54.850818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2be3fe29d88298fedb19b347db50ddb2de4fb7587688f38eeeb6fa7927d53aac","sha256:94abdb2edda16cb148547e0b67c9a9bdbf2511035be145e638d7cc05e5c354d3"],"state_sha256":"3c43ff5640355e814c0a0d28d09ad6aae2c32e5cd2fc2a13a87334f4761c08f0"}