{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLRYMFOBNVG2IKN6LVEMEIL6KE","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":"9943407b710753cf41415796399438d4572a3c7d7dbffdc89b5b299773dade7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T15:30:47Z","title_canon_sha256":"315a4f1c39141160a157b1e00506e84a582c98fbfbe969f501619455875d6459"},"schema_version":"1.0","source":{"id":"2605.22620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22620","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22620v1","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22620","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"WLRYMFOBNVG2","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"WLRYMFOBNVG2IKN6","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"WLRYMFOB","created_at":"2026-05-22T01:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:116b1ec153f43671e76a712e110115e6164125a66021a6eef9a23e7a43b61cdc","target":"graph","created_at":"2026-05-22T01:05:00Z","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/2605.22620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from internal feedback (RLIF) has recently emerged as a scalable unsupervised alternative, using signals extracted from the model itself. However, existing RLIF methods typically rely on a single internal reward, which can lead to reward hacking, entropy collapse, and degraded reasoning structure. We propose a multi-reward RLIF framework that decomposes the training sig","authors_text":"Ahsan Habib Akash, Binod Bhattarai, Diganta Sikdar, Prashnna Gyawali, Shourov Joarder","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T15:30:47Z","title":"Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22620","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":"sha256:3314090c0c2abb1f17e7462761bbb28b24813779f97baa24038246683c9fe6ff","target":"record","created_at":"2026-05-22T01:05:00Z","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":"9943407b710753cf41415796399438d4572a3c7d7dbffdc89b5b299773dade7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T15:30:47Z","title_canon_sha256":"315a4f1c39141160a157b1e00506e84a582c98fbfbe969f501619455875d6459"},"schema_version":"1.0","source":{"id":"2605.22620","kind":"arxiv","version":1}},"canonical_sha256":"b2e38615c16d4da429be5d48c2217e512ef42886a2dcccbce79ef319966dd8ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2e38615c16d4da429be5d48c2217e512ef42886a2dcccbce79ef319966dd8ea","first_computed_at":"2026-05-22T01:05:00.877020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:05:00.877020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MXx996Nto7U4q+VaUt13kdlitMmK11ENskRubqsDan6F7SO1up2bBeFWWb5cn3BAe1UX8tTMQoO1F8ePDES0AA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:05:00.877615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3314090c0c2abb1f17e7462761bbb28b24813779f97baa24038246683c9fe6ff","sha256:116b1ec153f43671e76a712e110115e6164125a66021a6eef9a23e7a43b61cdc"],"state_sha256":"2d9a3bf203e4aae298d51ed9bee308cdf40ca8ec6bbfad72cab8a4beae0b29d9"}