{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z75IBECO6DCUAOTKAEKSRSIY3V","short_pith_number":"pith:Z75IBECO","canonical_record":{"source":{"id":"2608.07371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T16:12:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2269aef3ee3f52ebf367538943bc996c5ad814e31bb3949a17c78894cb0b0574","abstract_canon_sha256":"2f025ff2d1c04d5f22ab15ff66f7052c0c026b5c66fffd66c0637b5f2a3f9172"},"schema_version":"1.0"},"canonical_sha256":"cffa80904ef0c5403a6a011528c918dd77e0ff247980c58bd51c7197566f926d","source":{"kind":"arxiv","id":"2608.07371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07371","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07371v1","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07371","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"Z75IBECO6DCU","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"Z75IBECO6DCUAOTK","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"Z75IBECO","created_at":"2026-08-10T01:15:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z75IBECO6DCUAOTKAEKSRSIY3V","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T16:12:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2269aef3ee3f52ebf367538943bc996c5ad814e31bb3949a17c78894cb0b0574","abstract_canon_sha256":"2f025ff2d1c04d5f22ab15ff66f7052c0c026b5c66fffd66c0637b5f2a3f9172"},"schema_version":"1.0"},"canonical_sha256":"cffa80904ef0c5403a6a011528c918dd77e0ff247980c58bd51c7197566f926d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:10.861727Z","signature_b64":"pkAt5RyXRnW7Hjxq9ua7/u7vrJHD4ynwS5COrommWOAdhZrPtrS29qoqaZnG7t1jvXqxoNXMrw3Etmo8Q8NtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cffa80904ef0c5403a6a011528c918dd77e0ff247980c58bd51c7197566f926d","last_reissued_at":"2026-08-10T01:15:10.859468Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:10.859468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07371","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":"2026-08-10T01:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHhrpxmZntwrivYacoyZHSqUMVLk6L+2e5q4nCrgo/XlVIQZTF3lc9QflvgwWzZZLCIPVrlvR9qgQUuEm6ynBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:45:32.992826Z"},"content_sha256":"cd3bae1c9be133f4b1985831af4bb72bb2444a3add13bf43a17c2903cdfa7f04","schema_version":"1.0","event_id":"sha256:cd3bae1c9be133f4b1985831af4bb72bb2444a3add13bf43a17c2903cdfa7f04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z75IBECO6DCUAOTKAEKSRSIY3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haoyu Zheng, Qing Wang, Wenqiao Zhang, Yun Zhu","submitted_at":"2026-08-07T16:12:58Z","abstract_excerpt":"Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07371","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/2608.07371/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":"2026-08-10T01:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bopd1Q6D9reK8WTmoCu65g22itmtMu1THWeXBOGg7hKrmbncUNRCUiIEQrNx0iIgMHVTAXOqikz8GrzIT3s1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:45:32.993150Z"},"content_sha256":"060267d2fb90972e7e2aff01de5172fcbbdec311dc31ff0945f345a72ef02223","schema_version":"1.0","event_id":"sha256:060267d2fb90972e7e2aff01de5172fcbbdec311dc31ff0945f345a72ef02223"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/bundle.json","state_url":"https://pith.science/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/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":"2026-08-20T03:45:32Z","links":{"resolver":"https://pith.science/pith/Z75IBECO6DCUAOTKAEKSRSIY3V","bundle":"https://pith.science/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/bundle.json","state":"https://pith.science/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z75IBECO6DCUAOTKAEKSRSIY3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z75IBECO6DCUAOTKAEKSRSIY3V","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":"2f025ff2d1c04d5f22ab15ff66f7052c0c026b5c66fffd66c0637b5f2a3f9172","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T16:12:58Z","title_canon_sha256":"2269aef3ee3f52ebf367538943bc996c5ad814e31bb3949a17c78894cb0b0574"},"schema_version":"1.0","source":{"id":"2608.07371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07371","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07371v1","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07371","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"Z75IBECO6DCU","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"Z75IBECO6DCUAOTK","created_at":"2026-08-10T01:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"Z75IBECO","created_at":"2026-08-10T01:15:10Z"}],"graph_snapshots":[{"event_id":"sha256:060267d2fb90972e7e2aff01de5172fcbbdec311dc31ff0945f345a72ef02223","target":"graph","created_at":"2026-08-10T01:15:10Z","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/2608.07371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-le","authors_text":"Haoyu Zheng, Qing Wang, Wenqiao Zhang, Yun Zhu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T16:12:58Z","title":"Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07371","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:cd3bae1c9be133f4b1985831af4bb72bb2444a3add13bf43a17c2903cdfa7f04","target":"record","created_at":"2026-08-10T01:15:10Z","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":"2f025ff2d1c04d5f22ab15ff66f7052c0c026b5c66fffd66c0637b5f2a3f9172","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T16:12:58Z","title_canon_sha256":"2269aef3ee3f52ebf367538943bc996c5ad814e31bb3949a17c78894cb0b0574"},"schema_version":"1.0","source":{"id":"2608.07371","kind":"arxiv","version":1}},"canonical_sha256":"cffa80904ef0c5403a6a011528c918dd77e0ff247980c58bd51c7197566f926d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cffa80904ef0c5403a6a011528c918dd77e0ff247980c58bd51c7197566f926d","first_computed_at":"2026-08-10T01:15:10.859468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:15:10.859468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pkAt5RyXRnW7Hjxq9ua7/u7vrJHD4ynwS5COrommWOAdhZrPtrS29qoqaZnG7t1jvXqxoNXMrw3Etmo8Q8NtAA==","signature_status":"signed_v1","signed_at":"2026-08-10T01:15:10.861727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd3bae1c9be133f4b1985831af4bb72bb2444a3add13bf43a17c2903cdfa7f04","sha256:060267d2fb90972e7e2aff01de5172fcbbdec311dc31ff0945f345a72ef02223"],"state_sha256":"13cc000d7925c62bbd5d048724123a6e242896558df0f53285a04ffd5bb2aa62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77zmQjdT3Ds83gzau1xWtJY7Z7uWs5TmBA9fygLB0Ju9ZmiXSgN3bW7UeDscax5yo3i86AR0EprerDAx4MOVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T03:45:32.997185Z","bundle_sha256":"df38ec290e80b7f6f618ac4c2c03682f78438cc3babd3b9d0cfca9922a62153a"}}