{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:JWP6S3JS53BGWAPBXQASBCFA7D","short_pith_number":"pith:JWP6S3JS","canonical_record":{"source":{"id":"1208.0984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-05T06:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"1da82ebf16a08000b83d078fd93613b9c0d44522ca5e46a9aef14ef9cc3f1f1f","abstract_canon_sha256":"b02620ef67ce558e2e89b9f7245e9de7921dbe920a6a574aa03c9e8f1fda7ab2"},"schema_version":"1.0"},"canonical_sha256":"4d9fe96d32eec26b01e1bc012088a0f8c34b326498007ea7f0d030457df0538e","source":{"kind":"arxiv","id":"1208.0984","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.0984","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"1208.0984v1","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.0984","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"JWP6S3JS53BG","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"JWP6S3JS53BGWAPB","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"JWP6S3JS","created_at":"2026-05-18T12:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:JWP6S3JS53BGWAPBXQASBCFA7D","target":"record","payload":{"canonical_record":{"source":{"id":"1208.0984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-05T06:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"1da82ebf16a08000b83d078fd93613b9c0d44522ca5e46a9aef14ef9cc3f1f1f","abstract_canon_sha256":"b02620ef67ce558e2e89b9f7245e9de7921dbe920a6a574aa03c9e8f1fda7ab2"},"schema_version":"1.0"},"canonical_sha256":"4d9fe96d32eec26b01e1bc012088a0f8c34b326498007ea7f0d030457df0538e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:20.904043Z","signature_b64":"bfQQhv+cfJJT2CnaYgIXuAmEYTQxrghyKNZo2Ssb+vxt6nyScePxobGr/eJtiBrJ5sq8f/k3w0P4Aor9Rhm0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d9fe96d32eec26b01e1bc012088a0f8c34b326498007ea7f0d030457df0538e","last_reissued_at":"2026-05-18T03:49:20.903265Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:20.903265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1208.0984","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":"2026-05-18T03:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9FcImnGZZjwd7WTaHKeAsqbYtFxw87nz14CLVfM4Z9AY9qpzy/p+Ok42MCHzAO/C/aL5IThOSvlxQlwa00bnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:19:31.550239Z"},"content_sha256":"6c9eb671d11a6825362b2b16da0d423392bd5e3647669665c2fe6033c4365c55","schema_version":"1.0","event_id":"sha256:6c9eb671d11a6825362b2b16da0d423392bd5e3647669665c2fe6033c4365c55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:JWP6S3JS53BGWAPBXQASBCFA7D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"APRIL: Active Preference-learning based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"LRI), Marc Schoenauer (INRIA Saclay - Ile de France, Mich\\`ele Sebag (LRI), Riad Akrour (INRIA Saclay - Ile de France","submitted_at":"2012-08-05T06:34:44Z","abstract_excerpt":"This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent demonstrations. Earlier work has presented an iterative preference-based RL framework: expert preferences are exploited to learn an approximate policy return, thus enabling the agent to achieve direct poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.0984","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":""},"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":"2026-05-18T03:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C5jhBo0duOnSElaaP+mAfYvKV/ebXXbHUl/mJ+Tt2pm9CWSnVEhASOaa7/pxMnfWzkCd6YzS6ggdg09/8mQ+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:19:31.550969Z"},"content_sha256":"f5caf5792d171dbb8aa5db9809da81c6653e6a37c4e4daf7e4ea1f9192cdba9d","schema_version":"1.0","event_id":"sha256:f5caf5792d171dbb8aa5db9809da81c6653e6a37c4e4daf7e4ea1f9192cdba9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JWP6S3JS53BGWAPBXQASBCFA7D/bundle.json","state_url":"https://pith.science/pith/JWP6S3JS53BGWAPBXQASBCFA7D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JWP6S3JS53BGWAPBXQASBCFA7D/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":"2026-06-09T02:19:31Z","links":{"resolver":"https://pith.science/pith/JWP6S3JS53BGWAPBXQASBCFA7D","bundle":"https://pith.science/pith/JWP6S3JS53BGWAPBXQASBCFA7D/bundle.json","state":"https://pith.science/pith/JWP6S3JS53BGWAPBXQASBCFA7D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JWP6S3JS53BGWAPBXQASBCFA7D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:JWP6S3JS53BGWAPBXQASBCFA7D","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":"b02620ef67ce558e2e89b9f7245e9de7921dbe920a6a574aa03c9e8f1fda7ab2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-05T06:34:44Z","title_canon_sha256":"1da82ebf16a08000b83d078fd93613b9c0d44522ca5e46a9aef14ef9cc3f1f1f"},"schema_version":"1.0","source":{"id":"1208.0984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.0984","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"1208.0984v1","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.0984","created_at":"2026-05-18T03:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"JWP6S3JS53BG","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"JWP6S3JS53BGWAPB","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"JWP6S3JS","created_at":"2026-05-18T12:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:f5caf5792d171dbb8aa5db9809da81c6653e6a37c4e4daf7e4ea1f9192cdba9d","target":"graph","created_at":"2026-05-18T03:49:20Z","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"},"paper":{"abstract_excerpt":"This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent demonstrations. Earlier work has presented an iterative preference-based RL framework: expert preferences are exploited to learn an approximate policy return, thus enabling the agent to achieve direct poli","authors_text":"LRI), Marc Schoenauer (INRIA Saclay - Ile de France, Mich\\`ele Sebag (LRI), Riad Akrour (INRIA Saclay - Ile de France","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-05T06:34:44Z","title":"APRIL: Active Preference-learning based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.0984","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":"sha256:6c9eb671d11a6825362b2b16da0d423392bd5e3647669665c2fe6033c4365c55","target":"record","created_at":"2026-05-18T03:49:20Z","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":"b02620ef67ce558e2e89b9f7245e9de7921dbe920a6a574aa03c9e8f1fda7ab2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-05T06:34:44Z","title_canon_sha256":"1da82ebf16a08000b83d078fd93613b9c0d44522ca5e46a9aef14ef9cc3f1f1f"},"schema_version":"1.0","source":{"id":"1208.0984","kind":"arxiv","version":1}},"canonical_sha256":"4d9fe96d32eec26b01e1bc012088a0f8c34b326498007ea7f0d030457df0538e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d9fe96d32eec26b01e1bc012088a0f8c34b326498007ea7f0d030457df0538e","first_computed_at":"2026-05-18T03:49:20.903265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:49:20.903265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bfQQhv+cfJJT2CnaYgIXuAmEYTQxrghyKNZo2Ssb+vxt6nyScePxobGr/eJtiBrJ5sq8f/k3w0P4Aor9Rhm0DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:49:20.904043Z","signed_message":"canonical_sha256_bytes"},"source_id":"1208.0984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c9eb671d11a6825362b2b16da0d423392bd5e3647669665c2fe6033c4365c55","sha256:f5caf5792d171dbb8aa5db9809da81c6653e6a37c4e4daf7e4ea1f9192cdba9d"],"state_sha256":"e88639cbe296a9e8084a3e622a70e98251fb8843430eac7608a70d1fd87d040e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4B57Ffi9R6MNGPUkeitZOwakpc8UlXNrohRdh3O+XfWOvm4drapxmta1f15Utsu+GoNudYO7oXxTSKUMpzgCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:19:31.554931Z","bundle_sha256":"3b2ca6fea0d000d4645532fc9f0b627324daa6879250883424ca128e775f4a47"}}