{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JMUFTAVUN5NPADHDBS6BLT6SQM","short_pith_number":"pith:JMUFTAVU","canonical_record":{"source":{"id":"2607.22039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T07:08:57Z","cross_cats_sorted":[],"title_canon_sha256":"5407ed25c34fcec710147b4481b011e8c171b7fc79086184fb1cfed5c0777939","abstract_canon_sha256":"6845169641bd008d627e972e3bf10ec8fa9a8c530adae3424876ca31bc24a943"},"schema_version":"1.0"},"canonical_sha256":"4b285982b46f5af00ce30cbc15cfd283173123ea158da0a968a5add60b0e95d1","source":{"kind":"arxiv","id":"2607.22039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22039","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22039v1","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22039","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"JMUFTAVUN5NP","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"JMUFTAVUN5NPADHD","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"JMUFTAVU","created_at":"2026-07-27T01:20:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JMUFTAVUN5NPADHDBS6BLT6SQM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T07:08:57Z","cross_cats_sorted":[],"title_canon_sha256":"5407ed25c34fcec710147b4481b011e8c171b7fc79086184fb1cfed5c0777939","abstract_canon_sha256":"6845169641bd008d627e972e3bf10ec8fa9a8c530adae3424876ca31bc24a943"},"schema_version":"1.0"},"canonical_sha256":"4b285982b46f5af00ce30cbc15cfd283173123ea158da0a968a5add60b0e95d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:44.637870Z","signature_b64":"2e954/35LVWSfxQA83xtj9CS5LGOVOf9rw+XWWEhJ2qPJZffJNIgIh3beqw5YkW1EB5v7ReuTtqmvu2rfM1aBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b285982b46f5af00ce30cbc15cfd283173123ea158da0a968a5add60b0e95d1","last_reissued_at":"2026-07-27T01:20:44.636975Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:44.636975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22039","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T01:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66i7rs/mKOyoxEEVjlL3lwXjOUVBeaPJ/gYHOQEvtXx0rQ1XJSDW9LmNOIvMXTWEzwt31ZPtqc2vaX9Ou8qADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:42:44.447487Z"},"content_sha256":"d1891b0beb3ab7c821d223e302cbe161ed29119c1ee0d273d09fb01c756d4594","schema_version":"1.0","event_id":"sha256:d1891b0beb3ab7c821d223e302cbe161ed29119c1ee0d273d09fb01c756d4594"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JMUFTAVUN5NPADHDBS6BLT6SQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Dai Dai, HaiFeng Wang, Hua Wu, Jinliang Lu, Junhong Wu, Yang Zhao, Zixuan Ren","submitted_at":"2026-07-24T07:08:57Z","abstract_excerpt":"Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22039","kind":"arxiv","version":1},"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/2607.22039/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":"2026-07-27T01:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tMxb9PIKbPOvNkbY/7/DLt/0M4uV0DaAt/UOY9Z7ztMDYC/n2RyJa1PgJl5mJ3J0Y2tiFHX0IaeCRgh4E5cDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:42:44.448040Z"},"content_sha256":"8f85d2b571f4a0a7926edc453f2e84f4c47481a94647e4b21d334e4ad28fe226","schema_version":"1.0","event_id":"sha256:8f85d2b571f4a0a7926edc453f2e84f4c47481a94647e4b21d334e4ad28fe226"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/bundle.json","state_url":"https://pith.science/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/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":"2026-08-03T17:42:44Z","links":{"resolver":"https://pith.science/pith/JMUFTAVUN5NPADHDBS6BLT6SQM","bundle":"https://pith.science/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/bundle.json","state":"https://pith.science/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMUFTAVUN5NPADHDBS6BLT6SQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JMUFTAVUN5NPADHDBS6BLT6SQM","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":"6845169641bd008d627e972e3bf10ec8fa9a8c530adae3424876ca31bc24a943","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T07:08:57Z","title_canon_sha256":"5407ed25c34fcec710147b4481b011e8c171b7fc79086184fb1cfed5c0777939"},"schema_version":"1.0","source":{"id":"2607.22039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22039","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22039v1","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22039","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"JMUFTAVUN5NP","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"JMUFTAVUN5NPADHD","created_at":"2026-07-27T01:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"JMUFTAVU","created_at":"2026-07-27T01:20:44Z"}],"graph_snapshots":[{"event_id":"sha256:8f85d2b571f4a0a7926edc453f2e84f4c47481a94647e4b21d334e4ad28fe226","target":"graph","created_at":"2026-07-27T01:20:44Z","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/2607.22039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehe","authors_text":"Chengqing Zong, Dai Dai, HaiFeng Wang, Hua Wu, Jinliang Lu, Junhong Wu, Yang Zhao, Zixuan Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T07:08:57Z","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22039","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:d1891b0beb3ab7c821d223e302cbe161ed29119c1ee0d273d09fb01c756d4594","target":"record","created_at":"2026-07-27T01:20:44Z","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":"6845169641bd008d627e972e3bf10ec8fa9a8c530adae3424876ca31bc24a943","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T07:08:57Z","title_canon_sha256":"5407ed25c34fcec710147b4481b011e8c171b7fc79086184fb1cfed5c0777939"},"schema_version":"1.0","source":{"id":"2607.22039","kind":"arxiv","version":1}},"canonical_sha256":"4b285982b46f5af00ce30cbc15cfd283173123ea158da0a968a5add60b0e95d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b285982b46f5af00ce30cbc15cfd283173123ea158da0a968a5add60b0e95d1","first_computed_at":"2026-07-27T01:20:44.636975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:44.636975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2e954/35LVWSfxQA83xtj9CS5LGOVOf9rw+XWWEhJ2qPJZffJNIgIh3beqw5YkW1EB5v7ReuTtqmvu2rfM1aBw==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:44.637870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1891b0beb3ab7c821d223e302cbe161ed29119c1ee0d273d09fb01c756d4594","sha256:8f85d2b571f4a0a7926edc453f2e84f4c47481a94647e4b21d334e4ad28fe226"],"state_sha256":"393fbb41de1dad57dd0f6cd1691207e485445ed6e4b0719ca020f3d96009213e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycK2Qt3WE2C8ukatMwX+dwMdMagv1sDMdMv+juz+F7y+uY6J/QBwYvQMxvYViZw8yg5N9S5pxCRQ91P3JBBCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:42:44.452994Z","bundle_sha256":"6af05338433574ce91f369098f6beb6e9e3e368418484097d6ecf54d0b2f13df"}}