{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EKOOWMWDXP5RJ2QZ65YUYFOWFH","short_pith_number":"pith:EKOOWMWD","canonical_record":{"source":{"id":"2507.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T07:54:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86b9f02c3a7906eb00c97dbd4c19508dcfc573f0806418cd898a1e74f39f7519","abstract_canon_sha256":"e6943f1463a809ff40fadddfd6af8c5536ce77c04a0af04a9e031100872a0af8"},"schema_version":"1.0"},"canonical_sha256":"229ceb32c3bbfb14ea19f7714c15d629f1a9718feede7300cb19c39cb2692263","source":{"kind":"arxiv","id":"2507.04730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04730","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04730v1","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04730","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_12","alias_value":"EKOOWMWDXP5R","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_16","alias_value":"EKOOWMWDXP5RJ2QZ","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_8","alias_value":"EKOOWMWD","created_at":"2026-07-05T11:32:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EKOOWMWDXP5RJ2QZ65YUYFOWFH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T07:54:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86b9f02c3a7906eb00c97dbd4c19508dcfc573f0806418cd898a1e74f39f7519","abstract_canon_sha256":"e6943f1463a809ff40fadddfd6af8c5536ce77c04a0af04a9e031100872a0af8"},"schema_version":"1.0"},"canonical_sha256":"229ceb32c3bbfb14ea19f7714c15d629f1a9718feede7300cb19c39cb2692263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:52.858734Z","signature_b64":"DHi/Ph8rMvzoAcUzBKwKrj3nl2zGlbsxaHFsqQDQCwsoMXSeratDbYtxHEcVYoYMe0YubawDl59u1BP3dUjqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"229ceb32c3bbfb14ea19f7714c15d629f1a9718feede7300cb19c39cb2692263","last_reissued_at":"2026-07-05T11:32:52.858101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:52.858101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04730","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":"2026-07-05T11:32:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+zTwVh7sj0DHxTHb2pQfd/103I1GpRXnHz1X4gCK1O4IP+2n/2aSqO5vEea4cBcp+dSXeN1pNKgByU2fJQ7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:13:58.229977Z"},"content_sha256":"41e69143b55fdcba4c43c86b2a9a40dff0d330277ad955ca12f98f5633a483c9","schema_version":"1.0","event_id":"sha256:41e69143b55fdcba4c43c86b2a9a40dff0d330277ad955ca12f98f5633a483c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EKOOWMWDXP5RJ2QZ65YUYFOWFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CueLearner: Bootstrapping and local policy adaptation from relative feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Cramariuc, Giulio Schiavi, Lionel Ott, Roland Siegwart","submitted_at":"2025-07-07T07:54:28Z","abstract_excerpt":"Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. Among these, relative feedback (i.e., feedback on how to improve an action, such as \"more to the left\") offers a good balance between usability and information richness. Previous research has shown that relative feedback can be used to enhance policy search methods. However, these efforts have been l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04730","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/2507.04730/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":"2026-07-05T11:32:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TF0ib5LGLnWycIYn3YD1RLjK94iXcRj7cx4QrG9YBs0mq1Qvy2W2O6PJYnHFISbdcCU47VQzySQrFFgtSlR8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:13:58.230537Z"},"content_sha256":"966de367d65e56e1928b3ad9693ac8036ebfad07ee3d05846ebe18af2fe5121d","schema_version":"1.0","event_id":"sha256:966de367d65e56e1928b3ad9693ac8036ebfad07ee3d05846ebe18af2fe5121d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/bundle.json","state_url":"https://pith.science/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/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":"2026-08-09T20:13:58Z","links":{"resolver":"https://pith.science/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH","bundle":"https://pith.science/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/bundle.json","state":"https://pith.science/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKOOWMWDXP5RJ2QZ65YUYFOWFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EKOOWMWDXP5RJ2QZ65YUYFOWFH","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":"e6943f1463a809ff40fadddfd6af8c5536ce77c04a0af04a9e031100872a0af8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T07:54:28Z","title_canon_sha256":"86b9f02c3a7906eb00c97dbd4c19508dcfc573f0806418cd898a1e74f39f7519"},"schema_version":"1.0","source":{"id":"2507.04730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04730","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04730v1","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04730","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_12","alias_value":"EKOOWMWDXP5R","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_16","alias_value":"EKOOWMWDXP5RJ2QZ","created_at":"2026-07-05T11:32:52Z"},{"alias_kind":"pith_short_8","alias_value":"EKOOWMWD","created_at":"2026-07-05T11:32:52Z"}],"graph_snapshots":[{"event_id":"sha256:966de367d65e56e1928b3ad9693ac8036ebfad07ee3d05846ebe18af2fe5121d","target":"graph","created_at":"2026-07-05T11:32:52Z","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/2507.04730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. Among these, relative feedback (i.e., feedback on how to improve an action, such as \"more to the left\") offers a good balance between usability and information richness. Previous research has shown that relative feedback can be used to enhance policy search methods. However, these efforts have been l","authors_text":"Andrei Cramariuc, Giulio Schiavi, Lionel Ott, Roland Siegwart","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T07:54:28Z","title":"CueLearner: Bootstrapping and local policy adaptation from relative feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04730","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":"sha256:41e69143b55fdcba4c43c86b2a9a40dff0d330277ad955ca12f98f5633a483c9","target":"record","created_at":"2026-07-05T11:32:52Z","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":"e6943f1463a809ff40fadddfd6af8c5536ce77c04a0af04a9e031100872a0af8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T07:54:28Z","title_canon_sha256":"86b9f02c3a7906eb00c97dbd4c19508dcfc573f0806418cd898a1e74f39f7519"},"schema_version":"1.0","source":{"id":"2507.04730","kind":"arxiv","version":1}},"canonical_sha256":"229ceb32c3bbfb14ea19f7714c15d629f1a9718feede7300cb19c39cb2692263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"229ceb32c3bbfb14ea19f7714c15d629f1a9718feede7300cb19c39cb2692263","first_computed_at":"2026-07-05T11:32:52.858101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:52.858101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DHi/Ph8rMvzoAcUzBKwKrj3nl2zGlbsxaHFsqQDQCwsoMXSeratDbYtxHEcVYoYMe0YubawDl59u1BP3dUjqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:52.858734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e69143b55fdcba4c43c86b2a9a40dff0d330277ad955ca12f98f5633a483c9","sha256:966de367d65e56e1928b3ad9693ac8036ebfad07ee3d05846ebe18af2fe5121d"],"state_sha256":"9cc6a2867315c633d35f31032250618b1e30b113bc9acb8c6235c635d8b0133b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qowoB+it6S6EhOn5AhfwKr1NkaEt47HWkKzKP1EXwYzX59tw5Hh/fGQolkmPLMHAOQUNcTA5+3ysJs0vOduCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:13:58.233908Z","bundle_sha256":"1c5290c806de4e76fb98c2a61fffd575386e9046d1eabb9c4d2c5f1c49cc9a2c"}}