{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:65Z3ITUIWIF3KCWNAL44NSLQYP","short_pith_number":"pith:65Z3ITUI","canonical_record":{"source":{"id":"2402.03244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:59:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2617ff7091781055ad87a35111d91aba3485ed2b6708e3d9b4ba58d05024a005","abstract_canon_sha256":"9d0cae3636bb1d16258e6100f4f62805fd71621bcdc0027b6b163d4d8fcf808b"},"schema_version":"1.0"},"canonical_sha256":"f773b44e88b20bb50acd02f9c6c970c3f27c5d14f93cace5f71e2ed6bf195fab","source":{"kind":"arxiv","id":"2402.03244","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03244","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03244v2","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03244","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_12","alias_value":"65Z3ITUIWIF3","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_16","alias_value":"65Z3ITUIWIF3KCWN","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_8","alias_value":"65Z3ITUI","created_at":"2026-07-05T08:35:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:65Z3ITUIWIF3KCWNAL44NSLQYP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.03244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:59:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2617ff7091781055ad87a35111d91aba3485ed2b6708e3d9b4ba58d05024a005","abstract_canon_sha256":"9d0cae3636bb1d16258e6100f4f62805fd71621bcdc0027b6b163d4d8fcf808b"},"schema_version":"1.0"},"canonical_sha256":"f773b44e88b20bb50acd02f9c6c970c3f27c5d14f93cace5f71e2ed6bf195fab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:41.607468Z","signature_b64":"4VADF+40oSUeqAAjkOtQthH1Wag7/psCUmOfHapazOp5LBKKLavbULng0Uhf4AxF+JFIFMzBRW9XH3wegqJ9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f773b44e88b20bb50acd02f9c6c970c3f27c5d14f93cace5f71e2ed6bf195fab","last_reissued_at":"2026-07-05T08:35:41.606973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:41.606973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.03244","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4Pn1wDM/VmzutnzM4A08736u2M0JfZB6tG0N0xtofmWC2M4TEB/wKwSlfu1FC/qX3jnJvgzepe8FnH+Gj5JBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:00:57.667434Z"},"content_sha256":"62fea605155e2b1dfcdd3100a5bc17112b2a1962d4b3cc1b8bb2c2e32da84260","schema_version":"1.0","event_id":"sha256:62fea605155e2b1dfcdd3100a5bc17112b2a1962d4b3cc1b8bb2c2e32da84260"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:65Z3ITUIWIF3KCWNAL44NSLQYP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Kolby Nottingham, Peter Clark, Roy Fox, Sameer Singh","submitted_at":"2024-02-05T17:59:00Z","abstract_excerpt":"Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is not straightforward. We propose Skill Set Optimization (SSO) for improving LLM actor performance through constructing and refining sets of transferable skills. SSO constructs skills by extracting common subtrajectories with high rewards and generating subgoals and instructions to represent each skill. These skills are provided to the LLM actor in-context to reinforce behaviors with high rewards. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03244","kind":"arxiv","version":2},"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/2402.03244/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":"2026-07-05T08:35:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvw+S0RJ23uRbMP2TBN2rc/6PP7C0z6YdRGCuxtLFyReaTq7MVEA9rXmSJzedPtrmV69pIv2Ug2/9hQcV+vsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:00:57.667812Z"},"content_sha256":"b56875c31bc48e92474330e8496e622c8ff9beace516ff610bf5f9e001950e73","schema_version":"1.0","event_id":"sha256:b56875c31bc48e92474330e8496e622c8ff9beace516ff610bf5f9e001950e73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/bundle.json","state_url":"https://pith.science/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/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":"2026-07-08T14:00:57Z","links":{"resolver":"https://pith.science/pith/65Z3ITUIWIF3KCWNAL44NSLQYP","bundle":"https://pith.science/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/bundle.json","state":"https://pith.science/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65Z3ITUIWIF3KCWNAL44NSLQYP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:65Z3ITUIWIF3KCWNAL44NSLQYP","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":"9d0cae3636bb1d16258e6100f4f62805fd71621bcdc0027b6b163d4d8fcf808b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:59:00Z","title_canon_sha256":"2617ff7091781055ad87a35111d91aba3485ed2b6708e3d9b4ba58d05024a005"},"schema_version":"1.0","source":{"id":"2402.03244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03244","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03244v2","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03244","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_12","alias_value":"65Z3ITUIWIF3","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_16","alias_value":"65Z3ITUIWIF3KCWN","created_at":"2026-07-05T08:35:41Z"},{"alias_kind":"pith_short_8","alias_value":"65Z3ITUI","created_at":"2026-07-05T08:35:41Z"}],"graph_snapshots":[{"event_id":"sha256:b56875c31bc48e92474330e8496e622c8ff9beace516ff610bf5f9e001950e73","target":"graph","created_at":"2026-07-05T08:35:41Z","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/2402.03244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is not straightforward. We propose Skill Set Optimization (SSO) for improving LLM actor performance through constructing and refining sets of transferable skills. SSO constructs skills by extracting common subtrajectories with high rewards and generating subgoals and instructions to represent each skill. These skills are provided to the LLM actor in-context to reinforce behaviors with high rewards. Th","authors_text":"Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Kolby Nottingham, Peter Clark, Roy Fox, Sameer Singh","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:59:00Z","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03244","kind":"arxiv","version":2},"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":"sha256:62fea605155e2b1dfcdd3100a5bc17112b2a1962d4b3cc1b8bb2c2e32da84260","target":"record","created_at":"2026-07-05T08:35:41Z","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":"9d0cae3636bb1d16258e6100f4f62805fd71621bcdc0027b6b163d4d8fcf808b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T17:59:00Z","title_canon_sha256":"2617ff7091781055ad87a35111d91aba3485ed2b6708e3d9b4ba58d05024a005"},"schema_version":"1.0","source":{"id":"2402.03244","kind":"arxiv","version":2}},"canonical_sha256":"f773b44e88b20bb50acd02f9c6c970c3f27c5d14f93cace5f71e2ed6bf195fab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f773b44e88b20bb50acd02f9c6c970c3f27c5d14f93cace5f71e2ed6bf195fab","first_computed_at":"2026-07-05T08:35:41.606973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:41.606973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4VADF+40oSUeqAAjkOtQthH1Wag7/psCUmOfHapazOp5LBKKLavbULng0Uhf4AxF+JFIFMzBRW9XH3wegqJ9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:41.607468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62fea605155e2b1dfcdd3100a5bc17112b2a1962d4b3cc1b8bb2c2e32da84260","sha256:b56875c31bc48e92474330e8496e622c8ff9beace516ff610bf5f9e001950e73"],"state_sha256":"9d7f1d5eb758931fc79c55519102c7ae0bfb5e43bccc0beb55d7abbcc39cc6e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6U2OPnEmtykfZ4WU0/bEE7LDqLUI2yDKqS4zbqAwu1ny0FT9OB2hzM1FmNyJpnbZHUcufBxPxidMag3eqJmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:00:57.669863Z","bundle_sha256":"ceaffc22310158abd2a5582e14eac68af49cb48172f8234e44203d68e92ec568"}}