{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R5ER4KTK7OQDV2SHIPMRNA3V4B","short_pith_number":"pith:R5ER4KTK","canonical_record":{"source":{"id":"2411.19547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a","abstract_canon_sha256":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124"},"schema_version":"1.0"},"canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","source":{"kind":"arxiv","id":"2411.19547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19547v1","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"R5ER4KTK7OQD","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_16","alias_value":"R5ER4KTK7OQDV2SH","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_8","alias_value":"R5ER4KTK","created_at":"2026-07-05T09:42:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R5ER4KTK7OQDV2SHIPMRNA3V4B","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a","abstract_canon_sha256":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124"},"schema_version":"1.0"},"canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:04.159562Z","signature_b64":"4JIAcE6gtp/ifiWHsvglCUmtFOYQo3Cpl3lBMiZG2eO5ELpTPoldVXTe7uN7ZNs2FGy73WAT3OckYxUbhUiRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","last_reissued_at":"2026-07-05T09:42:04.159045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:04.159045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19547","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":"2026-07-05T09:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wBylyNs2BUh8MqeUrMwqgCsmlKllowRzlLAR3a+ElmWLR2TsDnHsQiG5rXbfgVRvfRUfPuU3tD/Uh+Vz5aF3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:20:54.099759Z"},"content_sha256":"b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f","schema_version":"1.0","event_id":"sha256:b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R5ER4KTK7OQDV2SHIPMRNA3V4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Agents with Weakly Supervised Feedback from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dihong Gong, Meng Zhou, Pu Lu, Xiuqiang He, Zelong Wang","submitted_at":"2024-11-29T08:47:04Z","abstract_excerpt":"Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely on definitive environmental feedback for reinforcement learning which limits their application to specific scenarios like gaming or code generation. This paper introduces a novel training method for LLM-based agents using weakly supervised signals from a critic LLM, bypassing the need for expert trajectories or definitive feedback. Our agents are trained in i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19547","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/2411.19547/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":"2026-07-05T09:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"keUgYuB6GmEZXE3zCvYmmzUghP4Bi5c3pmSo5L5eOGi3WEsWIPOQk4ksgwwuvQ34NWV7qlUJOv1TJNtZsQOWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:20:54.100713Z"},"content_sha256":"a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef","schema_version":"1.0","event_id":"sha256:a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/bundle.json","state_url":"https://pith.science/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/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":"2026-08-18T06:20:54Z","links":{"resolver":"https://pith.science/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B","bundle":"https://pith.science/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/bundle.json","state":"https://pith.science/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5ER4KTK7OQDV2SHIPMRNA3V4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R5ER4KTK7OQDV2SHIPMRNA3V4B","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":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a"},"schema_version":"1.0","source":{"id":"2411.19547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19547v1","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19547","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"R5ER4KTK7OQD","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_16","alias_value":"R5ER4KTK7OQDV2SH","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_8","alias_value":"R5ER4KTK","created_at":"2026-07-05T09:42:04Z"}],"graph_snapshots":[{"event_id":"sha256:a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef","target":"graph","created_at":"2026-07-05T09:42:04Z","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/2411.19547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely on definitive environmental feedback for reinforcement learning which limits their application to specific scenarios like gaming or code generation. This paper introduces a novel training method for LLM-based agents using weakly supervised signals from a critic LLM, bypassing the need for expert trajectories or definitive feedback. Our agents are trained in i","authors_text":"Dihong Gong, Meng Zhou, Pu Lu, Xiuqiang He, Zelong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title":"Training Agents with Weakly Supervised Feedback from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19547","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:b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f","target":"record","created_at":"2026-07-05T09:42:04Z","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":"71f613f1b073458e606194d737d77ad0bc30cd8344569cec27b9405738026124","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-29T08:47:04Z","title_canon_sha256":"d1f57081c1960822e9bb5dca039fa16fd18667de4ad0679cb1ffec698f7f105a"},"schema_version":"1.0","source":{"id":"2411.19547","kind":"arxiv","version":1}},"canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f491e2a6afba03aea4743d9168375e060af541fd3c7505b1b3e0628c4657fb3","first_computed_at":"2026-07-05T09:42:04.159045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:04.159045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4JIAcE6gtp/ifiWHsvglCUmtFOYQo3Cpl3lBMiZG2eO5ELpTPoldVXTe7uN7ZNs2FGy73WAT3OckYxUbhUiRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:04.159562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a91a238acc2f696f90a21180a7a22e9d2709d21b39cea04e38c83c0f519c0f","sha256:a461cbbf50cecc29fde90c71eef2510dd191867071e473b508347e584b1b53ef"],"state_sha256":"72d3c03571c8f3d0e2db26c36ff45f48e760f4d04bd0c9e0a0de36b2d14704f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pTycZxM/1QjNvcdbtXTwRY0YHjSE+a3Tk0OfOHRWeZR0nFKTsKFTwPrWn1qVY42QSA+Ayaf3YUQH6uDW9135AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:20:54.105933Z","bundle_sha256":"75a5dfcda9f8fd0a739db19661fca55d140feaef6e6b767a12cffceaaa0f2bfc"}}