{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3AFTNEK3MSFGICHUYLNY4NGDDV","short_pith_number":"pith:3AFTNEK3","canonical_record":{"source":{"id":"2205.14288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-28T01:03:30Z","cross_cats_sorted":[],"title_canon_sha256":"da3e6834b36f71dafdc862fb8c02d82e59a1f41320963278ccf7ececa0f94f13","abstract_canon_sha256":"e4e534f0b9f474ae88ea252bca54a4ef84dee8827372fc4fc45a84ecd11f7727"},"schema_version":"1.0"},"canonical_sha256":"d80b36915b648a6408f4c2db8e34c31d70d572b326e4cb9de1a46a13ae377513","source":{"kind":"arxiv","id":"2205.14288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14288","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14288v1","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14288","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_12","alias_value":"3AFTNEK3MSFG","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_16","alias_value":"3AFTNEK3MSFGICHU","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_8","alias_value":"3AFTNEK3","created_at":"2026-07-05T04:27:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3AFTNEK3MSFGICHUYLNY4NGDDV","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-28T01:03:30Z","cross_cats_sorted":[],"title_canon_sha256":"da3e6834b36f71dafdc862fb8c02d82e59a1f41320963278ccf7ececa0f94f13","abstract_canon_sha256":"e4e534f0b9f474ae88ea252bca54a4ef84dee8827372fc4fc45a84ecd11f7727"},"schema_version":"1.0"},"canonical_sha256":"d80b36915b648a6408f4c2db8e34c31d70d572b326e4cb9de1a46a13ae377513","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:15.939581Z","signature_b64":"GJGMILtBSl+XApVZFvyEAuMGUzhNmcwzwsyR0liFNduwAWayx/HX8r9sVY76twHWHOE5eSxEeW6i4RgxV+UIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d80b36915b648a6408f4c2db8e34c31d70d572b326e4cb9de1a46a13ae377513","last_reissued_at":"2026-07-05T04:27:15.939180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:15.939180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14288","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":"2026-07-05T04:27:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e32yeIiXtR9zki98Dv8tnAWGO8TZki7uX8K0xmRJrPESGETqKbE19v9SFfNj8xWXHaimGkzFGlTGXhGJGSs+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:49:27.991368Z"},"content_sha256":"a56dba30fdc4a569e8b4b8e68726103ae87832a3421d402226fb5576866f46e3","schema_version":"1.0","event_id":"sha256:a56dba30fdc4a569e8b4b8e68726103ae87832a3421d402226fb5576866f46e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3AFTNEK3MSFGICHUYLNY4NGDDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-shot Subgoal Planning with Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Honglak Lee, Lajanugen Logeswaran, Moontae Lee, Yao Fu","submitted_at":"2022-05-28T01:03:30Z","abstract_excerpt":"Pre-trained large language models have shown successful progress in many language understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction, we show that language priors encoded in pre-trained language models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences from few training sequences without any fine-tuning. We further propose a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14288","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/2205.14288/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":"2026-07-05T04:27:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhHly3mFiCC61DnXmW9zreP/ug6+5sz+Ows7d35Ovco8AwRXT6JKg8v2lBkTwrIMqE9lFchH6N3aoiS6xEbmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:49:27.991752Z"},"content_sha256":"afe4ad22a16a58bf544daf62dbb209b38ca3bfaae6b60b049c18a87f6759a8ef","schema_version":"1.0","event_id":"sha256:afe4ad22a16a58bf544daf62dbb209b38ca3bfaae6b60b049c18a87f6759a8ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/bundle.json","state_url":"https://pith.science/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/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":"2026-08-19T20:49:27Z","links":{"resolver":"https://pith.science/pith/3AFTNEK3MSFGICHUYLNY4NGDDV","bundle":"https://pith.science/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/bundle.json","state":"https://pith.science/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AFTNEK3MSFGICHUYLNY4NGDDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3AFTNEK3MSFGICHUYLNY4NGDDV","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":"e4e534f0b9f474ae88ea252bca54a4ef84dee8827372fc4fc45a84ecd11f7727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-28T01:03:30Z","title_canon_sha256":"da3e6834b36f71dafdc862fb8c02d82e59a1f41320963278ccf7ececa0f94f13"},"schema_version":"1.0","source":{"id":"2205.14288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14288","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14288v1","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14288","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_12","alias_value":"3AFTNEK3MSFG","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_16","alias_value":"3AFTNEK3MSFGICHU","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_8","alias_value":"3AFTNEK3","created_at":"2026-07-05T04:27:15Z"}],"graph_snapshots":[{"event_id":"sha256:afe4ad22a16a58bf544daf62dbb209b38ca3bfaae6b60b049c18a87f6759a8ef","target":"graph","created_at":"2026-07-05T04:27:15Z","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/2205.14288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained large language models have shown successful progress in many language understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction, we show that language priors encoded in pre-trained language models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences from few training sequences without any fine-tuning. We further propose a si","authors_text":"Honglak Lee, Lajanugen Logeswaran, Moontae Lee, Yao Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-28T01:03:30Z","title":"Few-shot Subgoal Planning with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14288","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:a56dba30fdc4a569e8b4b8e68726103ae87832a3421d402226fb5576866f46e3","target":"record","created_at":"2026-07-05T04:27:15Z","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":"e4e534f0b9f474ae88ea252bca54a4ef84dee8827372fc4fc45a84ecd11f7727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-28T01:03:30Z","title_canon_sha256":"da3e6834b36f71dafdc862fb8c02d82e59a1f41320963278ccf7ececa0f94f13"},"schema_version":"1.0","source":{"id":"2205.14288","kind":"arxiv","version":1}},"canonical_sha256":"d80b36915b648a6408f4c2db8e34c31d70d572b326e4cb9de1a46a13ae377513","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d80b36915b648a6408f4c2db8e34c31d70d572b326e4cb9de1a46a13ae377513","first_computed_at":"2026-07-05T04:27:15.939180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:15.939180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJGMILtBSl+XApVZFvyEAuMGUzhNmcwzwsyR0liFNduwAWayx/HX8r9sVY76twHWHOE5eSxEeW6i4RgxV+UIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:15.939581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a56dba30fdc4a569e8b4b8e68726103ae87832a3421d402226fb5576866f46e3","sha256:afe4ad22a16a58bf544daf62dbb209b38ca3bfaae6b60b049c18a87f6759a8ef"],"state_sha256":"97f06e81c73c0e241ff8e93d43d086261fb3d12e09ad53c00403e5bc10295c8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0vJ7qhOMooKEmt4wZuRnKwdjUu32D6vTbFVcqWqeuludvIjMv02VoNK2pry9taeSksDjKQZerVDmlLsRLz6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:49:27.995013Z","bundle_sha256":"fa1b4f30eac5aac61900f12fed1fd1a4e50e48988f4d9ac489d684cad8e18aac"}}