{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T4UY6XZFLHA4A4K5SAQEA4A7G4","short_pith_number":"pith:T4UY6XZF","canonical_record":{"source":{"id":"2310.14403","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-22T20:28:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a02d3750d86b98e24582cc7b4698f3e9f50c7f6a3079d046646ecdca73f5ccbd","abstract_canon_sha256":"1afa54bbf9a643763912a43bd12f6b885425da2ea6dd001185dafea36171fdc0"},"schema_version":"1.0"},"canonical_sha256":"9f298f5f2559c1c0715d902040701f3729c33a398d6c964c1bc74d7a42d0910a","source":{"kind":"arxiv","id":"2310.14403","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14403","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14403v5","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14403","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"T4UY6XZFLHA4","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"T4UY6XZFLHA4A4K5","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"T4UY6XZF","created_at":"2026-07-05T07:49:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T4UY6XZFLHA4A4K5SAQEA4A7G4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14403","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-22T20:28:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a02d3750d86b98e24582cc7b4698f3e9f50c7f6a3079d046646ecdca73f5ccbd","abstract_canon_sha256":"1afa54bbf9a643763912a43bd12f6b885425da2ea6dd001185dafea36171fdc0"},"schema_version":"1.0"},"canonical_sha256":"9f298f5f2559c1c0715d902040701f3729c33a398d6c964c1bc74d7a42d0910a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:15.505168Z","signature_b64":"cHsXlWqm/RmGN6zy2ra+i/KFVVOyaWOFT8I9CbkuK9DUj2owqKffXnn7PnZGt3mrP/i0cmbWO3AsQLK18UAxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f298f5f2559c1c0715d902040701f3729c33a398d6c964c1bc74d7a42d0910a","last_reissued_at":"2026-07-05T07:49:15.504653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:15.504653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14403","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gt9keXk2NMBw1hmEzWjdrtpNrG/L3J1RsUUsMnwbCQlpwSSgluva6zExWhoNUCSj+t5AGHjgB9W4Yks2D16ODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:20:57.316025Z"},"content_sha256":"1e523c79f78f9ffc1003c0e058cc6050ebdf7d4ec6977714afff0e8053567ce6","schema_version":"1.0","event_id":"sha256:1e523c79f78f9ffc1003c0e058cc6050ebdf7d4ec6977714afff0e8053567ce6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T4UY6XZFLHA4A4K5SAQEA4A7G4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Deepeka Garg, Jared Vann, Mengda Xu, Sumitra Ganesh, Udari Madhushani, Yanchao Sun, Yuchen Xiao","submitted_at":"2023-10-22T20:28:33Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems. By imitating few-shot examples provided in the prompts (i.e., in-context learning), an LLM agent can interact with an external environment and complete given tasks without additional training. However, such few-shot examples are often insufficient to generate high-quality solutions for complex and long-horizon tasks, while the limited context length cannot consume larger-scale demonstrations with long interaction horizons. To this end, we propose an offline l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14403","kind":"arxiv","version":5},"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/2310.14403/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":"2026-07-05T07:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ha+REbmSTEvWpjKJfgm3MBaOds1aMQWgwDYpGs0/JO165+kq/BiR2kwz7AtZptnTh/sKtU+0CrD7YtoZGiyPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:20:57.316734Z"},"content_sha256":"6545e4b0978aa52f5ae373553521516f321246d0b9b5beeda627b66b3fc8e025","schema_version":"1.0","event_id":"sha256:6545e4b0978aa52f5ae373553521516f321246d0b9b5beeda627b66b3fc8e025"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/bundle.json","state_url":"https://pith.science/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/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":"2026-07-08T07:20:57Z","links":{"resolver":"https://pith.science/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4","bundle":"https://pith.science/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/bundle.json","state":"https://pith.science/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4UY6XZFLHA4A4K5SAQEA4A7G4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T4UY6XZFLHA4A4K5SAQEA4A7G4","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":"1afa54bbf9a643763912a43bd12f6b885425da2ea6dd001185dafea36171fdc0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-22T20:28:33Z","title_canon_sha256":"a02d3750d86b98e24582cc7b4698f3e9f50c7f6a3079d046646ecdca73f5ccbd"},"schema_version":"1.0","source":{"id":"2310.14403","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14403","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14403v5","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14403","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"T4UY6XZFLHA4","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"T4UY6XZFLHA4A4K5","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"T4UY6XZF","created_at":"2026-07-05T07:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:6545e4b0978aa52f5ae373553521516f321246d0b9b5beeda627b66b3fc8e025","target":"graph","created_at":"2026-07-05T07:49:15Z","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/2310.14403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems. By imitating few-shot examples provided in the prompts (i.e., in-context learning), an LLM agent can interact with an external environment and complete given tasks without additional training. However, such few-shot examples are often insufficient to generate high-quality solutions for complex and long-horizon tasks, while the limited context length cannot consume larger-scale demonstrations with long interaction horizons. To this end, we propose an offline l","authors_text":"Deepeka Garg, Jared Vann, Mengda Xu, Sumitra Ganesh, Udari Madhushani, Yanchao Sun, Yuchen Xiao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-22T20:28:33Z","title":"O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14403","kind":"arxiv","version":5},"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":"sha256:1e523c79f78f9ffc1003c0e058cc6050ebdf7d4ec6977714afff0e8053567ce6","target":"record","created_at":"2026-07-05T07:49:15Z","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":"1afa54bbf9a643763912a43bd12f6b885425da2ea6dd001185dafea36171fdc0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-22T20:28:33Z","title_canon_sha256":"a02d3750d86b98e24582cc7b4698f3e9f50c7f6a3079d046646ecdca73f5ccbd"},"schema_version":"1.0","source":{"id":"2310.14403","kind":"arxiv","version":5}},"canonical_sha256":"9f298f5f2559c1c0715d902040701f3729c33a398d6c964c1bc74d7a42d0910a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f298f5f2559c1c0715d902040701f3729c33a398d6c964c1bc74d7a42d0910a","first_computed_at":"2026-07-05T07:49:15.504653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:15.504653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cHsXlWqm/RmGN6zy2ra+i/KFVVOyaWOFT8I9CbkuK9DUj2owqKffXnn7PnZGt3mrP/i0cmbWO3AsQLK18UAxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:15.505168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14403","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e523c79f78f9ffc1003c0e058cc6050ebdf7d4ec6977714afff0e8053567ce6","sha256:6545e4b0978aa52f5ae373553521516f321246d0b9b5beeda627b66b3fc8e025"],"state_sha256":"9d9eac4a1b5073c423450592f49ae899fbc2ccf6c4f3dc92be0595ca95c8595f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+civtCcnLIgsnV64+2nxTPUiEYbQSnpE+HAv3pG1i5V4r8NC21u72p7SIUreQWNTCSgsNFrh8Kj9veT458XFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:20:57.320635Z","bundle_sha256":"d8752bbea9301806fcc00424399621d6717a20464d694e15054f0ccc9db592f3"}}