{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KHAR6WRZSHXFO3WKWTVE6T6KD6","short_pith_number":"pith:KHAR6WRZ","canonical_record":{"source":{"id":"2505.16401","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"d3fbd2cf083eb97ab56e4c0130484b28eb370d182832ca3d9497f9659e415141","abstract_canon_sha256":"44f7111cc1951860bba1f6ca64ec9a3393107cae99e4fd602f5990c27524d923"},"schema_version":"1.0"},"canonical_sha256":"51c11f5a3991ee576ecab4ea4f4fca1fa2731df4d2638c0d9499ae45b01f0f29","source":{"kind":"arxiv","id":"2505.16401","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16401","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16401v4","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16401","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"KHAR6WRZSHXF","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_16","alias_value":"KHAR6WRZSHXFO3WK","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_8","alias_value":"KHAR6WRZ","created_at":"2026-07-05T11:20:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KHAR6WRZSHXFO3WKWTVE6T6KD6","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16401","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"d3fbd2cf083eb97ab56e4c0130484b28eb370d182832ca3d9497f9659e415141","abstract_canon_sha256":"44f7111cc1951860bba1f6ca64ec9a3393107cae99e4fd602f5990c27524d923"},"schema_version":"1.0"},"canonical_sha256":"51c11f5a3991ee576ecab4ea4f4fca1fa2731df4d2638c0d9499ae45b01f0f29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:12.307355Z","signature_b64":"Y3Axyd50hyzX+9UUPNB5ejrwL1p87kLz1CVTuIGgzSNhcdElYmZWiJ5EviG4TdoMkyEtRqlQVvdSZTrc8817Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51c11f5a3991ee576ecab4ea4f4fca1fa2731df4d2638c0d9499ae45b01f0f29","last_reissued_at":"2026-07-05T11:20:12.306843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:12.306843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16401","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xn31gVVBC04KOmtP3Rodk74twHS9c92DNjnCow9yP0BzTtDGgP251eAyMcsUMECrY/8zoWX5Ot6B5UIgVO6dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:25:28.265338Z"},"content_sha256":"234d59fdff2f066bf5357d20336f4c2f3a80bbb8d493cc5a869a5951ea6cc378","schema_version":"1.0","event_id":"sha256:234d59fdff2f066bf5357d20336f4c2f3a80bbb8d493cc5a869a5951ea6cc378"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KHAR6WRZSHXFO3WKWTVE6T6KD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Divide-Fuse-Conquer: Eliciting \"Aha Moments\" in Multi-Scenario Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ang Lv, Flood Sung, Huabin Zheng, Rui Yan, Xiaoqing Zhang, Xiuying Chen, Yuhan Liu, Zirui Song","submitted_at":"2025-05-22T08:52:21Z","abstract_excerpt":"Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL), resembling an ``aha moment'' triggered by simple outcome-based rewards. While RL has proven effective in eliciting such breakthroughs in tasks involving mathematics, coding, and vision, it faces significant challenges in multi-scenario games. The diversity of game rules, interaction modes, and environmental complexities often leads to policies that perform well in one scenario but fail to generalize to others. Simply combining multiple scenarios during training i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16401","kind":"arxiv","version":4},"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/2505.16401/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":"2026-07-05T11:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gez/STfPBj1KK4u5rIMFhUiCQ8VaMh+GWkZS11RFR8bJ3Hm4Xg3Hqgs0ZPVfYCBqwGAjIt8OYi2XEJmphKTEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:25:28.265821Z"},"content_sha256":"347686d7ae9547ec5a6334a75ba3e8aa2d2c51d013f657018a2c3dfdc8456e48","schema_version":"1.0","event_id":"sha256:347686d7ae9547ec5a6334a75ba3e8aa2d2c51d013f657018a2c3dfdc8456e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/bundle.json","state_url":"https://pith.science/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/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":"2026-08-01T07:25:28Z","links":{"resolver":"https://pith.science/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6","bundle":"https://pith.science/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/bundle.json","state":"https://pith.science/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHAR6WRZSHXFO3WKWTVE6T6KD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KHAR6WRZSHXFO3WKWTVE6T6KD6","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":"44f7111cc1951860bba1f6ca64ec9a3393107cae99e4fd602f5990c27524d923","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:52:21Z","title_canon_sha256":"d3fbd2cf083eb97ab56e4c0130484b28eb370d182832ca3d9497f9659e415141"},"schema_version":"1.0","source":{"id":"2505.16401","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16401","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16401v4","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16401","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"KHAR6WRZSHXF","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_16","alias_value":"KHAR6WRZSHXFO3WK","created_at":"2026-07-05T11:20:12Z"},{"alias_kind":"pith_short_8","alias_value":"KHAR6WRZ","created_at":"2026-07-05T11:20:12Z"}],"graph_snapshots":[{"event_id":"sha256:347686d7ae9547ec5a6334a75ba3e8aa2d2c51d013f657018a2c3dfdc8456e48","target":"graph","created_at":"2026-07-05T11:20:12Z","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/2505.16401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL), resembling an ``aha moment'' triggered by simple outcome-based rewards. While RL has proven effective in eliciting such breakthroughs in tasks involving mathematics, coding, and vision, it faces significant challenges in multi-scenario games. The diversity of game rules, interaction modes, and environmental complexities often leads to policies that perform well in one scenario but fail to generalize to others. Simply combining multiple scenarios during training i","authors_text":"Ang Lv, Flood Sung, Huabin Zheng, Rui Yan, Xiaoqing Zhang, Xiuying Chen, Yuhan Liu, Zirui Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:52:21Z","title":"Divide-Fuse-Conquer: Eliciting \"Aha Moments\" in Multi-Scenario Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16401","kind":"arxiv","version":4},"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":"sha256:234d59fdff2f066bf5357d20336f4c2f3a80bbb8d493cc5a869a5951ea6cc378","target":"record","created_at":"2026-07-05T11:20:12Z","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":"44f7111cc1951860bba1f6ca64ec9a3393107cae99e4fd602f5990c27524d923","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T08:52:21Z","title_canon_sha256":"d3fbd2cf083eb97ab56e4c0130484b28eb370d182832ca3d9497f9659e415141"},"schema_version":"1.0","source":{"id":"2505.16401","kind":"arxiv","version":4}},"canonical_sha256":"51c11f5a3991ee576ecab4ea4f4fca1fa2731df4d2638c0d9499ae45b01f0f29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51c11f5a3991ee576ecab4ea4f4fca1fa2731df4d2638c0d9499ae45b01f0f29","first_computed_at":"2026-07-05T11:20:12.306843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:12.306843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y3Axyd50hyzX+9UUPNB5ejrwL1p87kLz1CVTuIGgzSNhcdElYmZWiJ5EviG4TdoMkyEtRqlQVvdSZTrc8817Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:12.307355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16401","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:234d59fdff2f066bf5357d20336f4c2f3a80bbb8d493cc5a869a5951ea6cc378","sha256:347686d7ae9547ec5a6334a75ba3e8aa2d2c51d013f657018a2c3dfdc8456e48"],"state_sha256":"5df86a4c91a3d29f729de2fba4f14efcef66899634ce79a459d2c04ffa576b68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3WXCkH7jlxVQEe9LAN3HmizVLYK2PDv7xYssc+242nxzDcE0SNOaBzvBZMM/dPOvmH/CSigSw2ICmT94ZYABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:25:28.269149Z","bundle_sha256":"4222eca8255b4eebd63e33a8cc0483b8a7fdc7e379da5ac90ba0284050368e67"}}