{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P43VXGCJD4UVEGBSZERP6VHXJ3","short_pith_number":"pith:P43VXGCJ","canonical_record":{"source":{"id":"2605.28699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"3d100b924859e06a7fbcc37776e79d936e053f20cc7815db282f86fe131b4cf6","abstract_canon_sha256":"1dee5d604f05cdb1a5049c48b170de194dc782902d7f78a4091c05b23e268f5b"},"schema_version":"1.0"},"canonical_sha256":"7f375b98491f29521832c922ff54f74ec5543bbea67a633d5f02c0fe1d188e6f","source":{"kind":"arxiv","id":"2605.28699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28699","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28699v1","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28699","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"P43VXGCJD4UV","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"P43VXGCJD4UVEGBS","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"P43VXGCJ","created_at":"2026-05-28T02:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P43VXGCJD4UVEGBSZERP6VHXJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"3d100b924859e06a7fbcc37776e79d936e053f20cc7815db282f86fe131b4cf6","abstract_canon_sha256":"1dee5d604f05cdb1a5049c48b170de194dc782902d7f78a4091c05b23e268f5b"},"schema_version":"1.0"},"canonical_sha256":"7f375b98491f29521832c922ff54f74ec5543bbea67a633d5f02c0fe1d188e6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:00.317712Z","signature_b64":"kUd5Z/3NfJr05ovjlnuqOaQMK8wBYmv2CFBml1pRlwOy++dCKkHM0pc5GyzWjq6suG4HfL+w41pRG2bu+AfBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f375b98491f29521832c922ff54f74ec5543bbea67a633d5f02c0fe1d188e6f","last_reissued_at":"2026-05-28T02:05:00.317289Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:00.317289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28699","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":"2026-05-28T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eP4gBFHKQmI8uGE0hR2H7YA1zUwcEBNza8NE3liWUKjcqCY+6zOsbdB0XASSdIIh1sBAZxUBnIFSyTWLO4NUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:22:42.639249Z"},"content_sha256":"6a590b6da43b20c7cc232f5f0cd424287ce86fd0f41f689a3b0fe339a0d93494","schema_version":"1.0","event_id":"sha256:6a590b6da43b20c7cc232f5f0cd424287ce86fd0f41f689a3b0fe339a0d93494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P43VXGCJD4UVEGBSZERP6VHXJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chusen Li, Shuigeng Zhou, Wentao Zhang, Zhou Liu","submitted_at":"2026-05-27T16:25:21Z","abstract_excerpt":"Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn multi-agent systems faces following dilemmas: i) Sparse rewards, role-level free-riding and excessive training overhead. ii) Agents only imitate to collaborate. iii) Fixed collaboration protocol falls into oscillating local optimum. We introduce TRACER, a turn-level reinforcement framework for cooperative multi-LLM reasoning. TRACER separates collaborative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28699","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/2605.28699/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":"2026-05-28T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O4l9rPsAdnXU9tW0VX1dMUPJnRBt8kYIg3ymOMkkU7DXeWP0MGj5eESwDVA0Vn8xj64Bjcoj5VEmlKW2DrxHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:22:42.639683Z"},"content_sha256":"108cfad4686a9b60de0e9c75bbc977e228fc6b15dbb7b83f77d0a372725f13ec","schema_version":"1.0","event_id":"sha256:108cfad4686a9b60de0e9c75bbc977e228fc6b15dbb7b83f77d0a372725f13ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/bundle.json","state_url":"https://pith.science/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/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":"2026-06-05T15:22:42Z","links":{"resolver":"https://pith.science/pith/P43VXGCJD4UVEGBSZERP6VHXJ3","bundle":"https://pith.science/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/bundle.json","state":"https://pith.science/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P43VXGCJD4UVEGBSZERP6VHXJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P43VXGCJD4UVEGBSZERP6VHXJ3","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":"1dee5d604f05cdb1a5049c48b170de194dc782902d7f78a4091c05b23e268f5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:21Z","title_canon_sha256":"3d100b924859e06a7fbcc37776e79d936e053f20cc7815db282f86fe131b4cf6"},"schema_version":"1.0","source":{"id":"2605.28699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28699","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28699v1","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28699","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"P43VXGCJD4UV","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"P43VXGCJD4UVEGBS","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"P43VXGCJ","created_at":"2026-05-28T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:108cfad4686a9b60de0e9c75bbc977e228fc6b15dbb7b83f77d0a372725f13ec","target":"graph","created_at":"2026-05-28T02:05:00Z","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/2605.28699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn multi-agent systems faces following dilemmas: i) Sparse rewards, role-level free-riding and excessive training overhead. ii) Agents only imitate to collaborate. iii) Fixed collaboration protocol falls into oscillating local optimum. We introduce TRACER, a turn-level reinforcement framework for cooperative multi-LLM reasoning. TRACER separates collaborative ","authors_text":"Chusen Li, Shuigeng Zhou, Wentao Zhang, Zhou Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:21Z","title":"TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28699","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":"sha256:6a590b6da43b20c7cc232f5f0cd424287ce86fd0f41f689a3b0fe339a0d93494","target":"record","created_at":"2026-05-28T02:05:00Z","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":"1dee5d604f05cdb1a5049c48b170de194dc782902d7f78a4091c05b23e268f5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:21Z","title_canon_sha256":"3d100b924859e06a7fbcc37776e79d936e053f20cc7815db282f86fe131b4cf6"},"schema_version":"1.0","source":{"id":"2605.28699","kind":"arxiv","version":1}},"canonical_sha256":"7f375b98491f29521832c922ff54f74ec5543bbea67a633d5f02c0fe1d188e6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f375b98491f29521832c922ff54f74ec5543bbea67a633d5f02c0fe1d188e6f","first_computed_at":"2026-05-28T02:05:00.317289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:00.317289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kUd5Z/3NfJr05ovjlnuqOaQMK8wBYmv2CFBml1pRlwOy++dCKkHM0pc5GyzWjq6suG4HfL+w41pRG2bu+AfBBw==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:00.317712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a590b6da43b20c7cc232f5f0cd424287ce86fd0f41f689a3b0fe339a0d93494","sha256:108cfad4686a9b60de0e9c75bbc977e228fc6b15dbb7b83f77d0a372725f13ec"],"state_sha256":"e15331cfdfe303306bff7acaeca257283eac8bfff689428738356a019518ea7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QW0QPGL3BRklaKZnJ0+ZZEMhSPZwiqTnAuVnnsX0NC+aaT5ohyo0IfxWlq0DbfG8LLD0uAImZlTrHUj/8pc5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:22:42.641747Z","bundle_sha256":"3bd57d71514d1b9c202efeff37796cf4466fbdb0fb404d31ece860ced27ded55"}}