{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VISZ7I6ZTTASZ3WV5KZOXZDX2Y","short_pith_number":"pith:VISZ7I6Z","canonical_record":{"source":{"id":"2408.16673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T16:21:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dab21606965239ba0a545adaa130a669b651207df1f5fc934739273321b5d8c","abstract_canon_sha256":"78c72aa3903c8123f71dff7e26119e18f515e706ce537d715a9f2fd352b0058e"},"schema_version":"1.0"},"canonical_sha256":"aa259fa3d99cc12ceed5eab2ebe477d616236bce0ea0dc6ad2f8c78798c3aa38","source":{"kind":"arxiv","id":"2408.16673","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16673","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16673v2","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16673","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"VISZ7I6ZTTAS","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"VISZ7I6ZTTASZ3WV","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"VISZ7I6Z","created_at":"2026-07-05T10:44:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VISZ7I6ZTTASZ3WV5KZOXZDX2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T16:21:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dab21606965239ba0a545adaa130a669b651207df1f5fc934739273321b5d8c","abstract_canon_sha256":"78c72aa3903c8123f71dff7e26119e18f515e706ce537d715a9f2fd352b0058e"},"schema_version":"1.0"},"canonical_sha256":"aa259fa3d99cc12ceed5eab2ebe477d616236bce0ea0dc6ad2f8c78798c3aa38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:39.714854Z","signature_b64":"6hgdl0yS5QV4Lthp/4deKxnqZKDyOlb9Rq5MuMfpEjAW0L7Tijylg1sa/xwWOGA/wid+17k0N5a0oT6+crEkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa259fa3d99cc12ceed5eab2ebe477d616236bce0ea0dc6ad2f8c78798c3aa38","last_reissued_at":"2026-07-05T10:44:39.714344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:39.714344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16673","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xHu51xPOLmqZkdTsZG4C2R5WV5D1cEnwBUfwSY+swVDjbX1Hp2bMMjBjwMv1+jd4WWd5OsTVvgrcSiFEel7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:12:35.731225Z"},"content_sha256":"e4fecac854f27d2a078d9616c6a4d8ea611363231a8f070242cfbae4d92dca55","schema_version":"1.0","event_id":"sha256:e4fecac854f27d2a078d9616c6a4d8ea611363231a8f070242cfbae4d92dca55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VISZ7I6ZTTASZ3WV5KZOXZDX2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Congliang Chen, Jiancong Xiao, Ruoyu Sun, Tian Xu, Zeyu Qin, Zhi-Quan Luo, Ziniu Li","submitted_at":"2024-08-29T16:21:00Z","abstract_excerpt":"Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However, CE maximizes the likelihood of observed data without accounting for alternative possibilities. As such, CE usually leads to reduced diversity in the model's outputs, which hinders further development that requires sampling to explore better responses. To address this limitation, this paper introduces a new game-theoretic formulation for SFT. In this framework, an auxiliary variable is introduced to regulate the learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16673","kind":"arxiv","version":2},"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/2408.16673/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFnmELnxuysj0XU+PeC5D2Mu9u+K6Wo3uPh0+5L6VgzmhFn8ZNx0m83l83aadDdvdACPQYJUCoe9LBqGFVtcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:12:35.731728Z"},"content_sha256":"a3e9f71e27f2c8b8ecfcacb805cc6c9bd97d3b9aaf614420a34e9d1ae2a4be31","schema_version":"1.0","event_id":"sha256:a3e9f71e27f2c8b8ecfcacb805cc6c9bd97d3b9aaf614420a34e9d1ae2a4be31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/bundle.json","state_url":"https://pith.science/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:12:35Z","links":{"resolver":"https://pith.science/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y","bundle":"https://pith.science/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/bundle.json","state":"https://pith.science/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VISZ7I6ZTTASZ3WV5KZOXZDX2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VISZ7I6ZTTASZ3WV5KZOXZDX2Y","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":"78c72aa3903c8123f71dff7e26119e18f515e706ce537d715a9f2fd352b0058e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T16:21:00Z","title_canon_sha256":"8dab21606965239ba0a545adaa130a669b651207df1f5fc934739273321b5d8c"},"schema_version":"1.0","source":{"id":"2408.16673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16673","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16673v2","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16673","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"VISZ7I6ZTTAS","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"VISZ7I6ZTTASZ3WV","created_at":"2026-07-05T10:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"VISZ7I6Z","created_at":"2026-07-05T10:44:39Z"}],"graph_snapshots":[{"event_id":"sha256:a3e9f71e27f2c8b8ecfcacb805cc6c9bd97d3b9aaf614420a34e9d1ae2a4be31","target":"graph","created_at":"2026-07-05T10:44:39Z","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/2408.16673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However, CE maximizes the likelihood of observed data without accounting for alternative possibilities. As such, CE usually leads to reduced diversity in the model's outputs, which hinders further development that requires sampling to explore better responses. To address this limitation, this paper introduces a new game-theoretic formulation for SFT. In this framework, an auxiliary variable is introduced to regulate the learn","authors_text":"Congliang Chen, Jiancong Xiao, Ruoyu Sun, Tian Xu, Zeyu Qin, Zhi-Quan Luo, Ziniu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T16:21:00Z","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16673","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:e4fecac854f27d2a078d9616c6a4d8ea611363231a8f070242cfbae4d92dca55","target":"record","created_at":"2026-07-05T10:44:39Z","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":"78c72aa3903c8123f71dff7e26119e18f515e706ce537d715a9f2fd352b0058e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T16:21:00Z","title_canon_sha256":"8dab21606965239ba0a545adaa130a669b651207df1f5fc934739273321b5d8c"},"schema_version":"1.0","source":{"id":"2408.16673","kind":"arxiv","version":2}},"canonical_sha256":"aa259fa3d99cc12ceed5eab2ebe477d616236bce0ea0dc6ad2f8c78798c3aa38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa259fa3d99cc12ceed5eab2ebe477d616236bce0ea0dc6ad2f8c78798c3aa38","first_computed_at":"2026-07-05T10:44:39.714344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:39.714344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6hgdl0yS5QV4Lthp/4deKxnqZKDyOlb9Rq5MuMfpEjAW0L7Tijylg1sa/xwWOGA/wid+17k0N5a0oT6+crEkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:39.714854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4fecac854f27d2a078d9616c6a4d8ea611363231a8f070242cfbae4d92dca55","sha256:a3e9f71e27f2c8b8ecfcacb805cc6c9bd97d3b9aaf614420a34e9d1ae2a4be31"],"state_sha256":"9f35b71989a55898e3e049ae2ace912748d8eb06d393abffd344596305176178"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfihTQAEftV1FoBLoSuveXabAtRXS5ABYkilXAtrf8hXQTx4/WtRkgIMz4VISZw6shWtmWHoVn7jwEd0T2UECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:12:35.735472Z","bundle_sha256":"355a1dcb6e0cd8f0accb5b6b57fe453de1171c4010410805f3f68ead75f52173"}}