{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YKQKF3RCLEYWKQTV4247AIAC7R","short_pith_number":"pith:YKQKF3RC","canonical_record":{"source":{"id":"2409.04617","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T21:00:57Z","cross_cats_sorted":[],"title_canon_sha256":"4beac0d64309293e4d8f35879dc89b07b978de41b8bda02ec6af0f768ed59468","abstract_canon_sha256":"7c015d2e43fa3f3adeed6c1830d4060597ab37ec6c1f48c80aadfba88005f903"},"schema_version":"1.0"},"canonical_sha256":"c2a0a2ee225931654275e6b9f02002fc4bde3fa1f65d3dd5f9399da0c6bb7bd0","source":{"kind":"arxiv","id":"2409.04617","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04617","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04617v3","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04617","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"YKQKF3RCLEYW","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_16","alias_value":"YKQKF3RCLEYWKQTV","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_8","alias_value":"YKQKF3RC","created_at":"2026-07-05T11:39:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YKQKF3RCLEYWKQTV4247AIAC7R","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04617","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T21:00:57Z","cross_cats_sorted":[],"title_canon_sha256":"4beac0d64309293e4d8f35879dc89b07b978de41b8bda02ec6af0f768ed59468","abstract_canon_sha256":"7c015d2e43fa3f3adeed6c1830d4060597ab37ec6c1f48c80aadfba88005f903"},"schema_version":"1.0"},"canonical_sha256":"c2a0a2ee225931654275e6b9f02002fc4bde3fa1f65d3dd5f9399da0c6bb7bd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:04.210675Z","signature_b64":"53EBz2g8LlMyhE5BTDY6sddUXkIYfgoAAJhHKl/qqtyr1wa/gtrKI2U+2igd9P0S1F5fMP770w2ZsIAamOHuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2a0a2ee225931654275e6b9f02002fc4bde3fa1f65d3dd5f9399da0c6bb7bd0","last_reissued_at":"2026-07-05T11:39:04.210197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:04.210197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04617","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":"2026-07-05T11:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"av1/e4nMGJj9Ay4jYMMT2dVkl3jVbezID1z/krDgKgAdyzR+R0uJ3w0sbGS5nZGHR9dCq0IyA9PmqMTKuNwCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:49:30.727382Z"},"content_sha256":"52860cd8efb09735df60306480e7f9c9aaf3bb5a1e2fc5dc21cc2e4a7fa78d8e","schema_version":"1.0","event_id":"sha256:52860cd8efb09735df60306480e7f9c9aaf3bb5a1e2fc5dc21cc2e4a7fa78d8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YKQKF3RCLEYWKQTV4247AIAC7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Rewards Can Self-Train Dialogue Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barrett Martin Lattimer, Ryan McDonald, Varun Gangal, Yi Yang","submitted_at":"2024-09-06T21:00:57Z","abstract_excerpt":"Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and high-quality human feedback. However, as base LLM models continue to improve, acquiring meaningful human feedback has become increasingly challenging and costly. In certain domains, base LLM agents may eventually exceed human capabilities, making traditional feedback-driven methods impractical. In this paper, we introduce a novel self-improvement paradigm that empowers LLM agents to autonomously enhance their perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04617","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/2409.04617/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":"2026-07-05T11:39:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MPZuvidBCIrDJ5mkUmn3cIZuGtga/BcLIiO6rlgznpIShmwBQphQeti3SFChw2xWAch8L1X0ivntZ6lFEApoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:49:30.728385Z"},"content_sha256":"ff096079a97d485585d3b5cae0d6b9bf2085b1d005e7126b977030c9d9f33627","schema_version":"1.0","event_id":"sha256:ff096079a97d485585d3b5cae0d6b9bf2085b1d005e7126b977030c9d9f33627"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKQKF3RCLEYWKQTV4247AIAC7R/bundle.json","state_url":"https://pith.science/pith/YKQKF3RCLEYWKQTV4247AIAC7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKQKF3RCLEYWKQTV4247AIAC7R/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":"2026-08-12T22:49:30Z","links":{"resolver":"https://pith.science/pith/YKQKF3RCLEYWKQTV4247AIAC7R","bundle":"https://pith.science/pith/YKQKF3RCLEYWKQTV4247AIAC7R/bundle.json","state":"https://pith.science/pith/YKQKF3RCLEYWKQTV4247AIAC7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKQKF3RCLEYWKQTV4247AIAC7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YKQKF3RCLEYWKQTV4247AIAC7R","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":"7c015d2e43fa3f3adeed6c1830d4060597ab37ec6c1f48c80aadfba88005f903","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T21:00:57Z","title_canon_sha256":"4beac0d64309293e4d8f35879dc89b07b978de41b8bda02ec6af0f768ed59468"},"schema_version":"1.0","source":{"id":"2409.04617","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04617","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04617v3","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04617","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_12","alias_value":"YKQKF3RCLEYW","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_16","alias_value":"YKQKF3RCLEYWKQTV","created_at":"2026-07-05T11:39:04Z"},{"alias_kind":"pith_short_8","alias_value":"YKQKF3RC","created_at":"2026-07-05T11:39:04Z"}],"graph_snapshots":[{"event_id":"sha256:ff096079a97d485585d3b5cae0d6b9bf2085b1d005e7126b977030c9d9f33627","target":"graph","created_at":"2026-07-05T11:39:04Z","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/2409.04617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and high-quality human feedback. However, as base LLM models continue to improve, acquiring meaningful human feedback has become increasingly challenging and costly. In certain domains, base LLM agents may eventually exceed human capabilities, making traditional feedback-driven methods impractical. In this paper, we introduce a novel self-improvement paradigm that empowers LLM agents to autonomously enhance their perform","authors_text":"Barrett Martin Lattimer, Ryan McDonald, Varun Gangal, Yi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T21:00:57Z","title":"Sparse Rewards Can Self-Train Dialogue Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04617","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":"sha256:52860cd8efb09735df60306480e7f9c9aaf3bb5a1e2fc5dc21cc2e4a7fa78d8e","target":"record","created_at":"2026-07-05T11:39:04Z","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":"7c015d2e43fa3f3adeed6c1830d4060597ab37ec6c1f48c80aadfba88005f903","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T21:00:57Z","title_canon_sha256":"4beac0d64309293e4d8f35879dc89b07b978de41b8bda02ec6af0f768ed59468"},"schema_version":"1.0","source":{"id":"2409.04617","kind":"arxiv","version":3}},"canonical_sha256":"c2a0a2ee225931654275e6b9f02002fc4bde3fa1f65d3dd5f9399da0c6bb7bd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2a0a2ee225931654275e6b9f02002fc4bde3fa1f65d3dd5f9399da0c6bb7bd0","first_computed_at":"2026-07-05T11:39:04.210197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:04.210197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53EBz2g8LlMyhE5BTDY6sddUXkIYfgoAAJhHKl/qqtyr1wa/gtrKI2U+2igd9P0S1F5fMP770w2ZsIAamOHuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:04.210675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04617","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52860cd8efb09735df60306480e7f9c9aaf3bb5a1e2fc5dc21cc2e4a7fa78d8e","sha256:ff096079a97d485585d3b5cae0d6b9bf2085b1d005e7126b977030c9d9f33627"],"state_sha256":"2d3e0604474f331179ad2e950562808afccc2106f686003394b401498933eb3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBAT90m8wpIoT2QSsroEdvpuA4i6Ag/3yNVOWlHZ1PV1F4zDuzu2L6lcjgajFi61Jbrj/pnezh5rymAQFYU3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:49:30.756031Z","bundle_sha256":"c09724e02d6cc0e8b0ed2abeb7320ef905458b3c7a6db11770dfe45233637723"}}