{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B5N4IXSYFLZBD3URRGD2VTPOO7","short_pith_number":"pith:B5N4IXSY","canonical_record":{"source":{"id":"2606.24669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T15:03:31Z","cross_cats_sorted":[],"title_canon_sha256":"b6cf7b688378fd1896d4454eb4ea8e0144ea04564b493f1e854c37564a42ab4b","abstract_canon_sha256":"30529322029e006e8c20ff083cd66b05d13241c6cdc2c5186d114c1149ae9e9b"},"schema_version":"1.0"},"canonical_sha256":"0f5bc45e582af211ee918987aacdee77e8b1cf62f39ec7e2aa2faa47846a1b9a","source":{"kind":"arxiv","id":"2606.24669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24669","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24669v1","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24669","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"B5N4IXSYFLZB","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"B5N4IXSYFLZBD3UR","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"B5N4IXSY","created_at":"2026-06-24T01:15:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B5N4IXSYFLZBD3URRGD2VTPOO7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T15:03:31Z","cross_cats_sorted":[],"title_canon_sha256":"b6cf7b688378fd1896d4454eb4ea8e0144ea04564b493f1e854c37564a42ab4b","abstract_canon_sha256":"30529322029e006e8c20ff083cd66b05d13241c6cdc2c5186d114c1149ae9e9b"},"schema_version":"1.0"},"canonical_sha256":"0f5bc45e582af211ee918987aacdee77e8b1cf62f39ec7e2aa2faa47846a1b9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:38.771739Z","signature_b64":"2FtavqMlNiDTh9AIQCYy/1HSn9ryZpDa5IB0GzwDv4C3Ne4atLl2HXXmd5qnYrKJClzFZYIMepCGTJBr4IaHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5bc45e582af211ee918987aacdee77e8b1cf62f39ec7e2aa2faa47846a1b9a","last_reissued_at":"2026-06-24T01:15:38.771348Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:38.771348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24669","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":"2026-06-24T01:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQiOux7qzbwBUitF8F3oXC3s2VIgO16y+mqu2JcjRvhsAnbC52Rw5wic3lqzSA4Oqv7WwTfzLurD1EYMMmbKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:22:15.612110Z"},"content_sha256":"02a843cd6d3443635b219f51316a53eed9f649fdbceed824f5150fd346773f23","schema_version":"1.0","event_id":"sha256:02a843cd6d3443635b219f51316a53eed9f649fdbceed824f5150fd346773f23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B5N4IXSYFLZBD3URRGD2VTPOO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaGO: Latent Action Guidance for Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu","submitted_at":"2026-06-23T15:03:31Z","abstract_excerpt":"Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be unreliable in practice. This paper proposes Latent Action Guidance for Online Reinforcement Learning (LaGO), a framework that uses a pretrained LLM as a latent action prior to softly guide online policy optimization, rather than treating the LLM as an explicit planner or controller. Experiments on both a discrete-control benchmark, CLEVR-Robot, and a continuous-control benchmark"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24669","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/2606.24669/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":"2026-06-24T01:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sPXruNKyY1TJZAb0oR0dTdmO5eRdTPkZCTJokdJsAQXe4hHYJKmD3aY4K+AZK71mwISlskOtnysEqlAXZbuFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:22:15.612489Z"},"content_sha256":"88bf1ad6b64c447dd0b9e4e46ecc8656b8858443b5c04f6d03fa7d0476e6d8bb","schema_version":"1.0","event_id":"sha256:88bf1ad6b64c447dd0b9e4e46ecc8656b8858443b5c04f6d03fa7d0476e6d8bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/bundle.json","state_url":"https://pith.science/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/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":"2026-07-06T23:22:15Z","links":{"resolver":"https://pith.science/pith/B5N4IXSYFLZBD3URRGD2VTPOO7","bundle":"https://pith.science/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/bundle.json","state":"https://pith.science/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5N4IXSYFLZBD3URRGD2VTPOO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B5N4IXSYFLZBD3URRGD2VTPOO7","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":"30529322029e006e8c20ff083cd66b05d13241c6cdc2c5186d114c1149ae9e9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T15:03:31Z","title_canon_sha256":"b6cf7b688378fd1896d4454eb4ea8e0144ea04564b493f1e854c37564a42ab4b"},"schema_version":"1.0","source":{"id":"2606.24669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24669","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24669v1","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24669","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"B5N4IXSYFLZB","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"B5N4IXSYFLZBD3UR","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"B5N4IXSY","created_at":"2026-06-24T01:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:88bf1ad6b64c447dd0b9e4e46ecc8656b8858443b5c04f6d03fa7d0476e6d8bb","target":"graph","created_at":"2026-06-24T01:15:38Z","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/2606.24669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be unreliable in practice. This paper proposes Latent Action Guidance for Online Reinforcement Learning (LaGO), a framework that uses a pretrained LLM as a latent action prior to softly guide online policy optimization, rather than treating the LLM as an explicit planner or controller. Experiments on both a discrete-control benchmark, CLEVR-Robot, and a continuous-control benchmark","authors_text":"Kuan-Yen Liu, Ren-Jyun Huang, Ti-Rong Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T15:03:31Z","title":"LaGO: Latent Action Guidance for Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24669","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":"sha256:02a843cd6d3443635b219f51316a53eed9f649fdbceed824f5150fd346773f23","target":"record","created_at":"2026-06-24T01:15:38Z","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":"30529322029e006e8c20ff083cd66b05d13241c6cdc2c5186d114c1149ae9e9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T15:03:31Z","title_canon_sha256":"b6cf7b688378fd1896d4454eb4ea8e0144ea04564b493f1e854c37564a42ab4b"},"schema_version":"1.0","source":{"id":"2606.24669","kind":"arxiv","version":1}},"canonical_sha256":"0f5bc45e582af211ee918987aacdee77e8b1cf62f39ec7e2aa2faa47846a1b9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f5bc45e582af211ee918987aacdee77e8b1cf62f39ec7e2aa2faa47846a1b9a","first_computed_at":"2026-06-24T01:15:38.771348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:38.771348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FtavqMlNiDTh9AIQCYy/1HSn9ryZpDa5IB0GzwDv4C3Ne4atLl2HXXmd5qnYrKJClzFZYIMepCGTJBr4IaHAQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:38.771739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02a843cd6d3443635b219f51316a53eed9f649fdbceed824f5150fd346773f23","sha256:88bf1ad6b64c447dd0b9e4e46ecc8656b8858443b5c04f6d03fa7d0476e6d8bb"],"state_sha256":"716af6fcee36ccf2724dc150e67833442a1f597ee9e442db5936d4926e2e6937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmP8AAbqLnpshH4nR595qglgpN9AGkQlBxAt0mXzKgHePj/uVbuy8wO4P4Y9xmSI37TzF0kaVaSARE0US7xaDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:22:15.614369Z","bundle_sha256":"c2434c120ea63f5cbfd1b3841e47c9255c524feeaab2202eeeb9b0bfd88a2461"}}