{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U5GQSYQJ4CLB3BP6PR3FMILX4L","short_pith_number":"pith:U5GQSYQJ","canonical_record":{"source":{"id":"2306.11483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:12:16Z","cross_cats_sorted":[],"title_canon_sha256":"9037de9ca6b462cb37ab70d1c33087e8b2d271053fc878be829845752a84f412","abstract_canon_sha256":"1eec5d56b1bd19cf75db68e01ede427338b1ba3960ab3a42111acdf8432f270f"},"schema_version":"1.0"},"canonical_sha256":"a74d096209e0961d85fe7c76562177e2fd2747e3ae9ebaaead31dc6ac8145589","source":{"kind":"arxiv","id":"2306.11483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11483","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11483v1","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11483","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"U5GQSYQJ4CLB","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"U5GQSYQJ4CLB3BP6","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"U5GQSYQJ","created_at":"2026-07-05T06:22:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U5GQSYQJ4CLB3BP6PR3FMILX4L","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:12:16Z","cross_cats_sorted":[],"title_canon_sha256":"9037de9ca6b462cb37ab70d1c33087e8b2d271053fc878be829845752a84f412","abstract_canon_sha256":"1eec5d56b1bd19cf75db68e01ede427338b1ba3960ab3a42111acdf8432f270f"},"schema_version":"1.0"},"canonical_sha256":"a74d096209e0961d85fe7c76562177e2fd2747e3ae9ebaaead31dc6ac8145589","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:20.273417Z","signature_b64":"65MC4WJwA4NcAO5apSRYL8dGWOK9K3Ql2ZxXFNDAoiH2b9/J/JWVdGUb++7PXPZYeqxnP0aJJQY8Zo4KN/gWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a74d096209e0961d85fe7c76562177e2fd2747e3ae9ebaaead31dc6ac8145589","last_reissued_at":"2026-07-05T06:22:20.272990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:20.272990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11483","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":"2026-07-05T06:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GKtMzLI3sSbz/EJ/Ebn2BRMGONuAyxZBnFg0eOz9ri6UNB2vX53KaULfQUjD+jBrf4+yYetML2kUlPFTtNF4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:12:45.316347Z"},"content_sha256":"a305bd6266204c5d045177d2f3459a348f23c84eefdc3f11574fdd97bc624674","schema_version":"1.0","event_id":"sha256:a305bd6266204c5d045177d2f3459a348f23c84eefdc3f11574fdd97bc624674"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U5GQSYQJ4CLB3BP6PR3FMILX4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Bulling, Anna Penzkofer, Florian Strohm, Mihai B\\^ace, Simon Schaefer, Stefan Leutenegger","submitted_at":"2023-06-20T12:12:16Z","abstract_excerpt":"While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11483","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/2306.11483/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":"2026-07-05T06:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wmydl7JGk6hNtxPjrfwUZUcDYkRoUPzcZUC+DQplqH8WZHfcjbJevc72KS8SDsR+wtl+E/JT5Zoi/pjiD7N8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:12:45.317294Z"},"content_sha256":"c8f407d3ac32933172b768202fbd5435e3c58dc6814f0b65bb723ae57a40d996","schema_version":"1.0","event_id":"sha256:c8f407d3ac32933172b768202fbd5435e3c58dc6814f0b65bb723ae57a40d996"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/bundle.json","state_url":"https://pith.science/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/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":"2026-08-13T10:12:45Z","links":{"resolver":"https://pith.science/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L","bundle":"https://pith.science/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/bundle.json","state":"https://pith.science/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5GQSYQJ4CLB3BP6PR3FMILX4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U5GQSYQJ4CLB3BP6PR3FMILX4L","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":"1eec5d56b1bd19cf75db68e01ede427338b1ba3960ab3a42111acdf8432f270f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:12:16Z","title_canon_sha256":"9037de9ca6b462cb37ab70d1c33087e8b2d271053fc878be829845752a84f412"},"schema_version":"1.0","source":{"id":"2306.11483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11483","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11483v1","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11483","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"U5GQSYQJ4CLB","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"U5GQSYQJ4CLB3BP6","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"U5GQSYQJ","created_at":"2026-07-05T06:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:c8f407d3ac32933172b768202fbd5435e3c58dc6814f0b65bb723ae57a40d996","target":"graph","created_at":"2026-07-05T06:22:20Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.11483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezum","authors_text":"Andreas Bulling, Anna Penzkofer, Florian Strohm, Mihai B\\^ace, Simon Schaefer, Stefan Leutenegger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:12:16Z","title":"Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11483","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:a305bd6266204c5d045177d2f3459a348f23c84eefdc3f11574fdd97bc624674","target":"record","created_at":"2026-07-05T06:22:20Z","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":"1eec5d56b1bd19cf75db68e01ede427338b1ba3960ab3a42111acdf8432f270f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-20T12:12:16Z","title_canon_sha256":"9037de9ca6b462cb37ab70d1c33087e8b2d271053fc878be829845752a84f412"},"schema_version":"1.0","source":{"id":"2306.11483","kind":"arxiv","version":1}},"canonical_sha256":"a74d096209e0961d85fe7c76562177e2fd2747e3ae9ebaaead31dc6ac8145589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a74d096209e0961d85fe7c76562177e2fd2747e3ae9ebaaead31dc6ac8145589","first_computed_at":"2026-07-05T06:22:20.272990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:20.272990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"65MC4WJwA4NcAO5apSRYL8dGWOK9K3Ql2ZxXFNDAoiH2b9/J/JWVdGUb++7PXPZYeqxnP0aJJQY8Zo4KN/gWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:20.273417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a305bd6266204c5d045177d2f3459a348f23c84eefdc3f11574fdd97bc624674","sha256:c8f407d3ac32933172b768202fbd5435e3c58dc6814f0b65bb723ae57a40d996"],"state_sha256":"fbd4764be94b7045158f399da5c29235dc0dea3c266dd4eafeeb8df22cdbb3e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EMxITSrJ17P837sa+TurKX7D9cB+W3ju7tuVLMswnSFDqQ0QjgX/xEeHm8nEW7wPd7ws4logD8NNyglSvaBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T10:12:45.324609Z","bundle_sha256":"0a1edf24afbdd65ffab7ba6695ea6272d3b7f0cd026f0efccae1a0560200f211"}}