{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JUCOORJ3LN2T2I3S2U422AZG44","short_pith_number":"pith:JUCOORJ3","canonical_record":{"source":{"id":"2602.11767","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T09:49:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b89f59f841d9740a6e0e396d30ae3d6e57b988f4d5cf7aaed60dd8692ef7be88","abstract_canon_sha256":"aca0aa5577d9682b42da57fa3909fc560f89b2b6ba8825a0198d01ca9d432448"},"schema_version":"1.0"},"canonical_sha256":"4d04e7453b5b753d2372d539ad0326e7130581c72d0edc3de2c8d84e1feeeb48","source":{"kind":"arxiv","id":"2602.11767","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11767","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11767v3","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11767","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"JUCOORJ3LN2T","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"JUCOORJ3LN2T2I3S","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"JUCOORJ3","created_at":"2026-05-20T01:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JUCOORJ3LN2T2I3S2U422AZG44","target":"record","payload":{"canonical_record":{"source":{"id":"2602.11767","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T09:49:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b89f59f841d9740a6e0e396d30ae3d6e57b988f4d5cf7aaed60dd8692ef7be88","abstract_canon_sha256":"aca0aa5577d9682b42da57fa3909fc560f89b2b6ba8825a0198d01ca9d432448"},"schema_version":"1.0"},"canonical_sha256":"4d04e7453b5b753d2372d539ad0326e7130581c72d0edc3de2c8d84e1feeeb48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:08.925681Z","signature_b64":"/b9HX9x545zLFD1B9cRFInhFO7l7KB2THdX2XuBVY2hD8/4G+JcpVCl0tFd0AoAtWE63K4KnNNOAUiy9Rsx2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d04e7453b5b753d2372d539ad0326e7130581c72d0edc3de2c8d84e1feeeb48","last_reissued_at":"2026-05-20T01:05:08.924641Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:08.924641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.11767","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0reuGUk61lecmh0AVb25IrX0rIdGZ+pfTa0XSd42sqdYF+KgGm6+YKs7u8w0aKqd3AgvhXox+FIU7K1vpy7zCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:19:02.132806Z"},"content_sha256":"2fe85974b670a0fee8e61e6b59255af22b58835ee96a528736d8e66cc861aa8d","schema_version":"1.0","event_id":"sha256:2fe85974b670a0fee8e61e6b59255af22b58835ee96a528736d8e66cc861aa8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JUCOORJ3LN2T2I3S2U422AZG44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Aladin Djuhera, Farhan Ahmed, Heiko Ludwig, Holger Boche, Swanand Ravindra Kadhe, Syed Zawad","submitted_at":"2026-02-12T09:49:24Z","abstract_excerpt":"Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However, multi-turn RL remains challenging as rewards are often sparse or delayed, and environments can be stochastic. In this regime, naive trajectory sampling can hinder exploitation and induce mode collapse. We propose TSR (Trajectory-Search Rollouts), a training-time approach that repurposes test-time scaling ideas for improved per-turn rollout generation. TSR performs lightweight tree-style search to construct high-qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11767","kind":"arxiv","version":3},"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/2602.11767/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":"2026-05-20T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9THQROCwYF8+lLu5r/CRLEP4/G/F/4DG5Hwe76Zb+xiIUmLnXdq+2M9/luIz/z0lgP7iq87P8y5JMOfze4ZjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:19:02.133184Z"},"content_sha256":"eba4016a6925504d2d4e7dee63b0d6f1e356ad7e519176cf83b8aee33f64e902","schema_version":"1.0","event_id":"sha256:eba4016a6925504d2d4e7dee63b0d6f1e356ad7e519176cf83b8aee33f64e902"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUCOORJ3LN2T2I3S2U422AZG44/bundle.json","state_url":"https://pith.science/pith/JUCOORJ3LN2T2I3S2U422AZG44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUCOORJ3LN2T2I3S2U422AZG44/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":"2026-06-01T20:19:02Z","links":{"resolver":"https://pith.science/pith/JUCOORJ3LN2T2I3S2U422AZG44","bundle":"https://pith.science/pith/JUCOORJ3LN2T2I3S2U422AZG44/bundle.json","state":"https://pith.science/pith/JUCOORJ3LN2T2I3S2U422AZG44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUCOORJ3LN2T2I3S2U422AZG44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JUCOORJ3LN2T2I3S2U422AZG44","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":"aca0aa5577d9682b42da57fa3909fc560f89b2b6ba8825a0198d01ca9d432448","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T09:49:24Z","title_canon_sha256":"b89f59f841d9740a6e0e396d30ae3d6e57b988f4d5cf7aaed60dd8692ef7be88"},"schema_version":"1.0","source":{"id":"2602.11767","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11767","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11767v3","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11767","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"JUCOORJ3LN2T","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"JUCOORJ3LN2T2I3S","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"JUCOORJ3","created_at":"2026-05-20T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:eba4016a6925504d2d4e7dee63b0d6f1e356ad7e519176cf83b8aee33f64e902","target":"graph","created_at":"2026-05-20T01:05:08Z","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/2602.11767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn interactions across tasks. However, multi-turn RL remains challenging as rewards are often sparse or delayed, and environments can be stochastic. In this regime, naive trajectory sampling can hinder exploitation and induce mode collapse. We propose TSR (Trajectory-Search Rollouts), a training-time approach that repurposes test-time scaling ideas for improved per-turn rollout generation. TSR performs lightweight tree-style search to construct high-qual","authors_text":"Aladin Djuhera, Farhan Ahmed, Heiko Ludwig, Holger Boche, Swanand Ravindra Kadhe, Syed Zawad","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T09:49:24Z","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11767","kind":"arxiv","version":3},"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":"sha256:2fe85974b670a0fee8e61e6b59255af22b58835ee96a528736d8e66cc861aa8d","target":"record","created_at":"2026-05-20T01:05:08Z","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":"aca0aa5577d9682b42da57fa3909fc560f89b2b6ba8825a0198d01ca9d432448","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T09:49:24Z","title_canon_sha256":"b89f59f841d9740a6e0e396d30ae3d6e57b988f4d5cf7aaed60dd8692ef7be88"},"schema_version":"1.0","source":{"id":"2602.11767","kind":"arxiv","version":3}},"canonical_sha256":"4d04e7453b5b753d2372d539ad0326e7130581c72d0edc3de2c8d84e1feeeb48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d04e7453b5b753d2372d539ad0326e7130581c72d0edc3de2c8d84e1feeeb48","first_computed_at":"2026-05-20T01:05:08.924641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:08.924641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/b9HX9x545zLFD1B9cRFInhFO7l7KB2THdX2XuBVY2hD8/4G+JcpVCl0tFd0AoAtWE63K4KnNNOAUiy9Rsx2Cw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:08.925681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.11767","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fe85974b670a0fee8e61e6b59255af22b58835ee96a528736d8e66cc861aa8d","sha256:eba4016a6925504d2d4e7dee63b0d6f1e356ad7e519176cf83b8aee33f64e902"],"state_sha256":"afb84e8d743b766320857dc67bd9cb9e49a73dc76ae0e284434b4caf2f1ab3d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4X8shS7xo8vnK8nNUeVqumo5JY/Tpx6z0klVCPXDXr76X+BYrwuZ+B0z5Ac6jznlQNB+mzsf2bRYG9KCIDpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:19:02.135363Z","bundle_sha256":"155714d6762a1d8eeac7905b443403cbdd0462789fafa6543e0e18dd04f8bb8a"}}