{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QQRGEENYTM3ROVF26YBABCYW6J","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":"bc5b07cfe7e66a7a7bbc108bb18baf00debce6df247ca3171713fb7652c49ec8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:46:33Z","title_canon_sha256":"aff5422e09711216e4bd481c50a42d3b0a6e9197fa56ec893833023694b10dbe"},"schema_version":"1.0","source":{"id":"2507.07817","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07817","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07817v2","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07817","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_12","alias_value":"QQRGEENYTM3R","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_16","alias_value":"QQRGEENYTM3ROVF2","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_8","alias_value":"QQRGEENY","created_at":"2026-07-05T11:37:25Z"}],"graph_snapshots":[{"event_id":"sha256:d2cd6006c973d4946855d09ff52eaa63a816070d54f92cf21834a0490fa741fc","target":"graph","created_at":"2026-07-05T11:37:25Z","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/2507.07817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction Tuning has emerged as a pivotal post-training paradigm that enables pre-trained language models to better follow user instructions. Despite its significance, little attention has been given to optimizing the loss function used. A fundamental, yet often overlooked, question is whether the conventional auto-regressive objective - where loss is computed only on response tokens, excluding prompt tokens - is truly optimal for instruction tuning. In this work, we systematically investigate the impact of differentially weighting prompt and response tokens in instruction tuning loss, and p","authors_text":"Anwoy Chatterjee, H S V N S Kowndinya Renduchintala, Sumit Bhatia, Tanmoy Chakraborty","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:46:33Z","title":"On the Effect of Instruction Tuning Loss on Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07817","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:c1fcaf3daa89f45ea743e61ceeb119c5329ecd15e94b3353f7b0b5ee4d54883d","target":"record","created_at":"2026-07-05T11:37:25Z","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":"bc5b07cfe7e66a7a7bbc108bb18baf00debce6df247ca3171713fb7652c49ec8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:46:33Z","title_canon_sha256":"aff5422e09711216e4bd481c50a42d3b0a6e9197fa56ec893833023694b10dbe"},"schema_version":"1.0","source":{"id":"2507.07817","kind":"arxiv","version":2}},"canonical_sha256":"84226211b89b371754baf602008b16f24740cb634e4af6c3b1aa372d023b140b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84226211b89b371754baf602008b16f24740cb634e4af6c3b1aa372d023b140b","first_computed_at":"2026-07-05T11:37:25.763473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:25.763473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tSt/f4GgtBpV6TxDAFWfGzzvZeevCaVv1IeMEzt19oBZDCsWDAfKleTCyO1TGuJzUc6Wxij+IQy2vxgjA2M3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:25.763965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07817","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1fcaf3daa89f45ea743e61ceeb119c5329ecd15e94b3353f7b0b5ee4d54883d","sha256:d2cd6006c973d4946855d09ff52eaa63a816070d54f92cf21834a0490fa741fc"],"state_sha256":"a541a2eca7f7abf15b8ce35e2671915a5b3c01d0cc5e830338a62a44dbb6e635"}