{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PYZTE7IJF6VHOF7G2YSDL4N2BV","short_pith_number":"pith:PYZTE7IJ","canonical_record":{"source":{"id":"2505.20023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"4558202739ef4d70647794e28d7f5c213618877a9980fb3f9e93e0568d69a902","abstract_canon_sha256":"5edbcc54f782fb71c85256936d938aca0e6ab13770079e9e2b7d17977d858f45"},"schema_version":"1.0"},"canonical_sha256":"7e33327d092faa7717e6d62435f1ba0d5a1b56eb86b303db3b9d6542e854153e","source":{"kind":"arxiv","id":"2505.20023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20023","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20023v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20023","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"PYZTE7IJF6VH","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"PYZTE7IJF6VHOF7G","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"PYZTE7IJ","created_at":"2026-07-05T11:09:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PYZTE7IJF6VHOF7G2YSDL4N2BV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"4558202739ef4d70647794e28d7f5c213618877a9980fb3f9e93e0568d69a902","abstract_canon_sha256":"5edbcc54f782fb71c85256936d938aca0e6ab13770079e9e2b7d17977d858f45"},"schema_version":"1.0"},"canonical_sha256":"7e33327d092faa7717e6d62435f1ba0d5a1b56eb86b303db3b9d6542e854153e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:51.417958Z","signature_b64":"b/Z0yhvSYA6WWARYt/gDntzvLweuG+tA1wyElqaCpOh+gHB76/uh5xmveqdVVwR14yyrndfcaaZxLzCzH8WlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e33327d092faa7717e6d62435f1ba0d5a1b56eb86b303db3b9d6542e854153e","last_reissued_at":"2026-07-05T11:09:51.417544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:51.417544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20023","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":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkzkRz4/aTSilirpQURba3+q/QLBZkdP+S8C45u8XajgE0gknDJ/MGjRWK7XCYq53GWFasE+oFgim/OJQmthAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:28.489001Z"},"content_sha256":"7c652b084d0e1484ce01f18765960524b3357b9b6b1b441341d719034499b838","schema_version":"1.0","event_id":"sha256:7c652b084d0e1484ce01f18765960524b3357b9b6b1b441341d719034499b838"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PYZTE7IJF6VHOF7G2YSDL4N2BV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Xiaorui Wang, Yihan Chen, Yongdong Zhang, Zhendong Mao","submitted_at":"2025-05-26T14:11:12Z","abstract_excerpt":"Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt engineering combined with closed-source LLMs like GPT-4. Although training open-source LLMs using expert trajectories from teacher models has yielded some improvements in agent capabilities, this approach still faces limitations such as performance plateauing and error propagation. To mitigate these challenges, we propose STeP, a novel method for improving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20023","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/2505.20023/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":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mghSQlTOWutBGMSrp4w3XKz1xNaLJlxLML7GSyMC4iQRpFEQFsHCOLXprm8cIIzIs9gkOie447aZoQiVrHYhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:28.489615Z"},"content_sha256":"d903f5c2b7c3440de8d6585aaa95d4c51afc5bdc352fbcc7e4d36eaaffbbb087","schema_version":"1.0","event_id":"sha256:d903f5c2b7c3440de8d6585aaa95d4c51afc5bdc352fbcc7e4d36eaaffbbb087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/bundle.json","state_url":"https://pith.science/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/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":"2026-08-08T20:10:28Z","links":{"resolver":"https://pith.science/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV","bundle":"https://pith.science/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/bundle.json","state":"https://pith.science/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYZTE7IJF6VHOF7G2YSDL4N2BV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PYZTE7IJF6VHOF7G2YSDL4N2BV","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":"5edbcc54f782fb71c85256936d938aca0e6ab13770079e9e2b7d17977d858f45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:11:12Z","title_canon_sha256":"4558202739ef4d70647794e28d7f5c213618877a9980fb3f9e93e0568d69a902"},"schema_version":"1.0","source":{"id":"2505.20023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20023","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20023v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20023","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"PYZTE7IJF6VH","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"PYZTE7IJF6VHOF7G","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"PYZTE7IJ","created_at":"2026-07-05T11:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:d903f5c2b7c3440de8d6585aaa95d4c51afc5bdc352fbcc7e4d36eaaffbbb087","target":"graph","created_at":"2026-07-05T11:09:51Z","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/2505.20023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt engineering combined with closed-source LLMs like GPT-4. Although training open-source LLMs using expert trajectories from teacher models has yielded some improvements in agent capabilities, this approach still faces limitations such as performance plateauing and error propagation. To mitigate these challenges, we propose STeP, a novel method for improving ","authors_text":"Benfeng Xu, Xiaorui Wang, Yihan Chen, Yongdong Zhang, Zhendong Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:11:12Z","title":"Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20023","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":"sha256:7c652b084d0e1484ce01f18765960524b3357b9b6b1b441341d719034499b838","target":"record","created_at":"2026-07-05T11:09:51Z","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":"5edbcc54f782fb71c85256936d938aca0e6ab13770079e9e2b7d17977d858f45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T14:11:12Z","title_canon_sha256":"4558202739ef4d70647794e28d7f5c213618877a9980fb3f9e93e0568d69a902"},"schema_version":"1.0","source":{"id":"2505.20023","kind":"arxiv","version":1}},"canonical_sha256":"7e33327d092faa7717e6d62435f1ba0d5a1b56eb86b303db3b9d6542e854153e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e33327d092faa7717e6d62435f1ba0d5a1b56eb86b303db3b9d6542e854153e","first_computed_at":"2026-07-05T11:09:51.417544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:51.417544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b/Z0yhvSYA6WWARYt/gDntzvLweuG+tA1wyElqaCpOh+gHB76/uh5xmveqdVVwR14yyrndfcaaZxLzCzH8WlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:51.417958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c652b084d0e1484ce01f18765960524b3357b9b6b1b441341d719034499b838","sha256:d903f5c2b7c3440de8d6585aaa95d4c51afc5bdc352fbcc7e4d36eaaffbbb087"],"state_sha256":"1bbb3ae8c9afd9bfc84115b31dfff7ffa28ab8dfeaf7ce777bb60272376ab3a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3OL2H4BIq8zdfZTlUuPMK6wOo5xKWnIufQL5DbYBjdfS46k64AlhLryNLFc6kbiVeflacoRBpTCI91IM2kPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:10:28.494496Z","bundle_sha256":"aef44898c3d7c9e6955a45b027b72f5a106778bca019c3656472ff16c3ed7c4f"}}