{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DSAMPC5NOOKQ7XV5CJZ6GZNULA","short_pith_number":"pith:DSAMPC5N","canonical_record":{"source":{"id":"2605.14237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T01:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"33b58ed1d5a9727f0f37a4127166359d48a89671b00a2c8ae77a3d166d62fe0a","abstract_canon_sha256":"195c6f70eee1272792a3bf24174929538b69aae9ad1fa126e3f8011c5bc6482a"},"schema_version":"1.0"},"canonical_sha256":"1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d","source":{"kind":"arxiv","id":"2605.14237","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14237","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14237v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14237","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"DSAMPC5NOOKQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSAMPC5NOOKQ7XV5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSAMPC5N","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DSAMPC5NOOKQ7XV5CJZ6GZNULA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T01:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"33b58ed1d5a9727f0f37a4127166359d48a89671b00a2c8ae77a3d166d62fe0a","abstract_canon_sha256":"195c6f70eee1272792a3bf24174929538b69aae9ad1fa126e3f8011c5bc6482a"},"schema_version":"1.0"},"canonical_sha256":"1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.687530Z","signature_b64":"Pzzyuted7uTCNmPtQoZvsaPC0k6prArRnJweyCp2YBRyzzcdW5WKTSiAsOnZXjTbXR/GXyxf5qVJ6ZHsfTnxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d","last_reissued_at":"2026-05-17T23:39:10.687059Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.687059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14237","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":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZDNcm/isIuY8uwjQldrJchwPgrr5/qjhb+s6ta/Ni8/L3RhpoCniLd0PHAwhmEJslnxnC0AZtN25YPyyDY+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:03:58.155982Z"},"content_sha256":"817cf24692ab6b6773384dda8d8086f72557f68b5fe10e68061e7493ac263e46","schema_version":"1.0","event_id":"sha256:817cf24692ab6b6773384dda8d8086f72557f68b5fe10e68061e7493ac263e46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DSAMPC5NOOKQ7XV5CJZ6GZNULA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Han, Kai Yu, Liang Wang, Xiaohua Wang, XuXiao Liang","submitted_at":"2026-05-14T01:05:35Z","abstract_excerpt":"Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestration, yet their inherent stochasticity causes unpredictable failures, and repeated invocations incur prohibitive token costs. We present the LOOP SKILL ENGINE, a system that achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm. On its first run, the agent executes the task with full LLM reasoning while the system transparently intercepts and records the"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that the greedy length-descending template extraction algorithm can always produce a branch-free Loop Skill that captures the task's functional intent without losing necessary conditional logic or requiring ongoing LLM reasoning","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The LOOP Skill Engine records one LLM-powered run of a periodic task and converts it into a deterministic replay template that eliminates further LLM usage while maintaining high success rates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8deadffb3d8610447ec2c2db813df5e6204cf95077a3a2c53649beacd5058ff1"},"source":{"id":"2605.14237","kind":"arxiv","version":1},"verdict":{"id":"44900f3e-6767-4cb0-9f75-75cdb66d1dc9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:34:36.125208Z","strongest_claim":"achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm","one_line_summary":"The LOOP Skill Engine records one LLM-powered run of a periodic task and converts it into a deterministic replay template that eliminates further LLM usage while maintaining high success rates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that the greedy length-descending template extraction algorithm can always produce a branch-free Loop Skill that captures the task's functional intent without losing necessary conditional logic or requiring ongoing LLM reasoning","pith_extraction_headline":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls."},"references":{"count":15,"sample":[{"doi":"","year":2023,"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","ref_index":1,"cited_arxiv_id":"2210.03629","is_internal_anchor":true},{"doi":"","year":2023,"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","ref_index":2,"cited_arxiv_id":"2302.04761","is_internal_anchor":true},{"doi":"","year":2023,"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","ref_index":3,"cited_arxiv_id":"2303.11366","is_internal_anchor":true},{"doi":"","year":2023,"title":"S. Gravitas. AutoGPT: Autonomous Task Management with LLMs. GitHub, 2023","work_id":"7737a352-c232-45bc-ae3c-10dd789df5d8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"LangChain: Building Applications with LLMs through Composability","work_id":"9bf0433e-0c75-4227-9cac-fc78fd80f267","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"970c408e8c8dad000a4c12d0d7a5cfecbdf03654107dc630602bf008271f421d","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da4ef021f595893d99574aede55a714f348d64877ec6009dab5aabd75738881b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"44900f3e-6767-4cb0-9f75-75cdb66d1dc9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FgmTJfcz8P9Qj+6M8gMnQm/ZqdwdLJABgMdfw1b9Qvq/Wy9KU78TL8wh0p6jx5IMsqm5LkgobjjbCFgrpKoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:03:58.157012Z"},"content_sha256":"4abac2667b1dd98b5fe8a1c0fbf633c4be3c3d00bdf8e92d1ddb82c45ed5b1f2","schema_version":"1.0","event_id":"sha256:4abac2667b1dd98b5fe8a1c0fbf633c4be3c3d00bdf8e92d1ddb82c45ed5b1f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/bundle.json","state_url":"https://pith.science/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/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":"2026-05-27T00:03:58Z","links":{"resolver":"https://pith.science/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA","bundle":"https://pith.science/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/bundle.json","state":"https://pith.science/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSAMPC5NOOKQ7XV5CJZ6GZNULA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSAMPC5NOOKQ7XV5CJZ6GZNULA","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":"195c6f70eee1272792a3bf24174929538b69aae9ad1fa126e3f8011c5bc6482a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T01:05:35Z","title_canon_sha256":"33b58ed1d5a9727f0f37a4127166359d48a89671b00a2c8ae77a3d166d62fe0a"},"schema_version":"1.0","source":{"id":"2605.14237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14237","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14237v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14237","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"DSAMPC5NOOKQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSAMPC5NOOKQ7XV5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSAMPC5N","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4abac2667b1dd98b5fe8a1c0fbf633c4be3c3d00bdf8e92d1ddb82c45ed5b1f2","target":"graph","created_at":"2026-05-17T23:39:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"that the greedy length-descending template extraction algorithm can always produce a branch-free Loop Skill that captures the task's functional intent without losing necessary conditional logic or requiring ongoing LLM reasoning"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The LOOP Skill Engine records one LLM-powered run of a periodic task and converts it into a deterministic replay template that eliminates further LLM usage while maintaining high success rates."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls."}],"snapshot_sha256":"8deadffb3d8610447ec2c2db813df5e6204cf95077a3a2c53649beacd5058ff1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"da4ef021f595893d99574aede55a714f348d64877ec6009dab5aabd75738881b"},"paper":{"abstract_excerpt":"Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestration, yet their inherent stochasticity causes unpredictable failures, and repeated invocations incur prohibitive token costs. We present the LOOP SKILL ENGINE, a system that achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm. On its first run, the agent executes the task with full LLM reasoning while the system transparently intercepts and records the","authors_text":"Chao Han, Kai Yu, Liang Wang, Xiaohua Wang, XuXiao Liang","cross_cats":[],"headline":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T01:05:35Z","title":"Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay"},"references":{"count":15,"internal_anchors":9,"resolved_work":15,"sample":[{"cited_arxiv_id":"2210.03629","doi":"","is_internal_anchor":true,"ref_index":1,"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","year":2023},{"cited_arxiv_id":"2302.04761","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","year":2023},{"cited_arxiv_id":"2303.11366","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"S. Gravitas. AutoGPT: Autonomous Task Management with LLMs. GitHub, 2023","work_id":"7737a352-c232-45bc-ae3c-10dd789df5d8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"LangChain: Building Applications with LLMs through Composability","work_id":"9bf0433e-0c75-4227-9cac-fc78fd80f267","year":2022}],"snapshot_sha256":"970c408e8c8dad000a4c12d0d7a5cfecbdf03654107dc630602bf008271f421d"},"source":{"id":"2605.14237","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:34:36.125208Z","id":"44900f3e-6767-4cb0-9f75-75cdb66d1dc9","model_set":{"reader":"grok-4.3"},"one_line_summary":"The LOOP Skill Engine records one LLM-powered run of a periodic task and converts it into a deterministic replay template that eliminates further LLM usage while maintaining high success rates.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls.","strongest_claim":"achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm","weakest_assumption":"that the greedy length-descending template extraction algorithm can always produce a branch-free Loop Skill that captures the task's functional intent without losing necessary conditional logic or requiring ongoing LLM reasoning"}},"verdict_id":"44900f3e-6767-4cb0-9f75-75cdb66d1dc9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:817cf24692ab6b6773384dda8d8086f72557f68b5fe10e68061e7493ac263e46","target":"record","created_at":"2026-05-17T23:39:10Z","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":"195c6f70eee1272792a3bf24174929538b69aae9ad1fa126e3f8011c5bc6482a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T01:05:35Z","title_canon_sha256":"33b58ed1d5a9727f0f37a4127166359d48a89671b00a2c8ae77a3d166d62fe0a"},"schema_version":"1.0","source":{"id":"2605.14237","kind":"arxiv","version":1}},"canonical_sha256":"1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d","first_computed_at":"2026-05-17T23:39:10.687059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.687059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pzzyuted7uTCNmPtQoZvsaPC0k6prArRnJweyCp2YBRyzzcdW5WKTSiAsOnZXjTbXR/GXyxf5qVJ6ZHsfTnxDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.687530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:817cf24692ab6b6773384dda8d8086f72557f68b5fe10e68061e7493ac263e46","sha256:4abac2667b1dd98b5fe8a1c0fbf633c4be3c3d00bdf8e92d1ddb82c45ed5b1f2"],"state_sha256":"20da9c3e091049b55201bc856627e39947e559b8b989abd6cfc42400c12d4bf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjq3783w3BWxP6kKq4S9zr1GSQDvnpuLtu2kY7BLfqVYz7fcNshnzVtChOKcpEiZSWGxjA/q1dgWqQcI+aymBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:03:58.161692Z","bundle_sha256":"4f9f69b4933e0efa2d79cfed09a170b86b832bc60a4a5358ff594523e1eeb0a1"}}