{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GMNSVW7GWJFISS7634BN6S3DPG","short_pith_number":"pith:GMNSVW7G","canonical_record":{"source":{"id":"2607.16257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T08:35:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7fbf50f6b02ca61c2100859d7f111b629891665c9d044d12de3601029133da67","abstract_canon_sha256":"c1a63f0f99bb295b330057b1a5c5bdb261916852fe52115b415f0900440ddff0"},"schema_version":"1.0"},"canonical_sha256":"331b2adbe6b24a894bfedf02df4b63799edbcd0a72cd0ffa4a619a5d94dc3bb2","source":{"kind":"arxiv","id":"2607.16257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16257","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16257v1","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16257","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"GMNSVW7GWJFI","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"GMNSVW7GWJFISS76","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"GMNSVW7G","created_at":"2026-07-21T00:20:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GMNSVW7GWJFISS7634BN6S3DPG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T08:35:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7fbf50f6b02ca61c2100859d7f111b629891665c9d044d12de3601029133da67","abstract_canon_sha256":"c1a63f0f99bb295b330057b1a5c5bdb261916852fe52115b415f0900440ddff0"},"schema_version":"1.0"},"canonical_sha256":"331b2adbe6b24a894bfedf02df4b63799edbcd0a72cd0ffa4a619a5d94dc3bb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:08.675747Z","signature_b64":"LDhlymg54jwERdeWc75PBsAJbiapSsK3P9L0RVhWH5K8jvuc1abbgyeuJQotwDwJkBly5w+hHbLJ5O2zoC/VCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"331b2adbe6b24a894bfedf02df4b63799edbcd0a72cd0ffa4a619a5d94dc3bb2","last_reissued_at":"2026-07-21T00:20:08.674877Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:08.674877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16257","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":"2026-07-21T00:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ziyTMt/LFvHU4NLvwYJTXKt15A6vyyUmPXqpY9n9ZOt65SN0lHudIgFTxMcH8DP7HHkov+UR210YfCuJY6c6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:38:41.458708Z"},"content_sha256":"cb095a4e112d39568a19fedc54b9863af5230159bfa305a84581d33b071fcefc","schema_version":"1.0","event_id":"sha256:cb095a4e112d39568a19fedc54b9863af5230159bfa305a84581d33b071fcefc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GMNSVW7GWJFISS7634BN6S3DPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiansheng Wei, Jiaqing Liang, Jinyi Han, Sihang Jiang, Tingyun Li, Xiaojun Meng, Xinyi Wang, Yanghua Xiao, Yizhou Ying, Zishang Jiang","submitted_at":"2026-06-28T08:35:47Z","abstract_excerpt":"Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16257","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/2607.16257/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":"2026-07-21T00:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIHtm3wcva8Lrk0+M7nXfwF9JlG1qsZzjUqtlwOLHgVzLYMTNILv2oc/ByS7zz471cTNptLrOLS2bnbTOr73Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:38:41.459233Z"},"content_sha256":"62c88b28f8158ac3349491be8cf6afd13d6a4cdf3b245f31b7259ae1eac7fc6e","schema_version":"1.0","event_id":"sha256:62c88b28f8158ac3349491be8cf6afd13d6a4cdf3b245f31b7259ae1eac7fc6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMNSVW7GWJFISS7634BN6S3DPG/bundle.json","state_url":"https://pith.science/pith/GMNSVW7GWJFISS7634BN6S3DPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMNSVW7GWJFISS7634BN6S3DPG/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":"2026-08-19T01:38:41Z","links":{"resolver":"https://pith.science/pith/GMNSVW7GWJFISS7634BN6S3DPG","bundle":"https://pith.science/pith/GMNSVW7GWJFISS7634BN6S3DPG/bundle.json","state":"https://pith.science/pith/GMNSVW7GWJFISS7634BN6S3DPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMNSVW7GWJFISS7634BN6S3DPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GMNSVW7GWJFISS7634BN6S3DPG","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":"c1a63f0f99bb295b330057b1a5c5bdb261916852fe52115b415f0900440ddff0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T08:35:47Z","title_canon_sha256":"7fbf50f6b02ca61c2100859d7f111b629891665c9d044d12de3601029133da67"},"schema_version":"1.0","source":{"id":"2607.16257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16257","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16257v1","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16257","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"GMNSVW7GWJFI","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"GMNSVW7GWJFISS76","created_at":"2026-07-21T00:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"GMNSVW7G","created_at":"2026-07-21T00:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:62c88b28f8158ac3349491be8cf6afd13d6a4cdf3b245f31b7259ae1eac7fc6e","target":"graph","created_at":"2026-07-21T00:20:08Z","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/2607.16257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extr","authors_text":"Jiansheng Wei, Jiaqing Liang, Jinyi Han, Sihang Jiang, Tingyun Li, Xiaojun Meng, Xinyi Wang, Yanghua Xiao, Yizhou Ying, Zishang Jiang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T08:35:47Z","title":"From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16257","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:cb095a4e112d39568a19fedc54b9863af5230159bfa305a84581d33b071fcefc","target":"record","created_at":"2026-07-21T00:20:08Z","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":"c1a63f0f99bb295b330057b1a5c5bdb261916852fe52115b415f0900440ddff0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T08:35:47Z","title_canon_sha256":"7fbf50f6b02ca61c2100859d7f111b629891665c9d044d12de3601029133da67"},"schema_version":"1.0","source":{"id":"2607.16257","kind":"arxiv","version":1}},"canonical_sha256":"331b2adbe6b24a894bfedf02df4b63799edbcd0a72cd0ffa4a619a5d94dc3bb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"331b2adbe6b24a894bfedf02df4b63799edbcd0a72cd0ffa4a619a5d94dc3bb2","first_computed_at":"2026-07-21T00:20:08.674877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:08.674877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LDhlymg54jwERdeWc75PBsAJbiapSsK3P9L0RVhWH5K8jvuc1abbgyeuJQotwDwJkBly5w+hHbLJ5O2zoC/VCA==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:08.675747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb095a4e112d39568a19fedc54b9863af5230159bfa305a84581d33b071fcefc","sha256:62c88b28f8158ac3349491be8cf6afd13d6a4cdf3b245f31b7259ae1eac7fc6e"],"state_sha256":"2e14e1e6692be06f54e55ce274fcd089954de0ce17d7986046e05ba45631f636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wLadM7UJvtMsF+107C66wiu4Cx4tE+3Un/3/LfU7j4VUBmSggOSLpQNyKWygJQZ0q4LnrpSJ7JmE0kzCsw6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:38:41.464684Z","bundle_sha256":"87199d2440fa09d9f788586b22c5095f31823f8269adaeae52ea577038742e0a"}}