{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NBG4WUTFLMQ5A6QQGFVHIQ4DKT","short_pith_number":"pith:NBG4WUTF","canonical_record":{"source":{"id":"2411.07760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:49:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"18438f0ab07dab7f115264a4598329fb031e299db0c2bcb8a7526ff93e4f875f","abstract_canon_sha256":"862195dc10d6e53437e0beab27bf07d396e2ab06ace02e85d1cd55a4845ecbd3"},"schema_version":"1.0"},"canonical_sha256":"684dcb52655b21d07a10316a74438354f1e66c5bec5c5b84ed878a545a27b62e","source":{"kind":"arxiv","id":"2411.07760","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07760","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07760v1","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07760","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_12","alias_value":"NBG4WUTFLMQ5","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_16","alias_value":"NBG4WUTFLMQ5A6QQ","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_8","alias_value":"NBG4WUTF","created_at":"2026-07-05T09:34:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NBG4WUTFLMQ5A6QQGFVHIQ4DKT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:49:41Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"18438f0ab07dab7f115264a4598329fb031e299db0c2bcb8a7526ff93e4f875f","abstract_canon_sha256":"862195dc10d6e53437e0beab27bf07d396e2ab06ace02e85d1cd55a4845ecbd3"},"schema_version":"1.0"},"canonical_sha256":"684dcb52655b21d07a10316a74438354f1e66c5bec5c5b84ed878a545a27b62e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:28.389938Z","signature_b64":"y5xjl7GxHOaRB58XyrlM+dxYTDrbQ2+sGLoIQW5yRINkMwa0rlUbKhQ0VonT6Ioy4UftE4lzUWm9DmIoAsZBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"684dcb52655b21d07a10316a74438354f1e66c5bec5c5b84ed878a545a27b62e","last_reissued_at":"2026-07-05T09:34:28.389565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:28.389565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07760","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":"2026-07-05T09:34:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1+0l0qd6lUaixRApqCLaW+dF1B+uYK0G0kRCDIWhLnT0ILWY1MWpZWhYsOZbmJHeELg+CQzWV6QJLGbZsFeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:04:02.055546Z"},"content_sha256":"6780e61be9497bd3b494df56e885d6facc1af8e885cdebf3fc26dd1a8ace0be8","schema_version":"1.0","event_id":"sha256:6780e61be9497bd3b494df56e885d6facc1af8e885cdebf3fc26dd1a8ace0be8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NBG4WUTFLMQ5A6QQGFVHIQ4DKT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexi Canesse, Ludovic Denoyer, Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","submitted_at":"2024-11-12T12:49:41Z","abstract_excerpt":"Offline Reinforcement Learning (RL) has emerged as a powerful alternative to imitation learning for behavior modeling in various domains, particularly in complex navigation tasks. An existing challenge with Offline RL is the signal-to-noise ratio, i.e. how to mitigate incorrect policy updates due to errors in value estimates. Towards this, multiple works have demonstrated the advantage of hierarchical offline RL methods, which decouples high-level path planning from low-level path following. In this work, we present a novel hierarchical transformer-based approach leveraging a learned quantizer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07760","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/2411.07760/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":"2026-07-05T09:34:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8cC1+QvTlYHG0s9B6KgajwBdkvIESiV+M9zxkMpf5YTsJ7i1fDXFajA3e2Yb9f14fRfOJg2h7LmF9tH8sAGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:04:02.056077Z"},"content_sha256":"5cb3f34c6afc54b9fcd3285d46881aa95dd7621c74c86c4d776196269231e638","schema_version":"1.0","event_id":"sha256:5cb3f34c6afc54b9fcd3285d46881aa95dd7621c74c86c4d776196269231e638"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/bundle.json","state_url":"https://pith.science/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/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":"2026-08-16T00:04:02Z","links":{"resolver":"https://pith.science/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT","bundle":"https://pith.science/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/bundle.json","state":"https://pith.science/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBG4WUTFLMQ5A6QQGFVHIQ4DKT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBG4WUTFLMQ5A6QQGFVHIQ4DKT","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":"862195dc10d6e53437e0beab27bf07d396e2ab06ace02e85d1cd55a4845ecbd3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:49:41Z","title_canon_sha256":"18438f0ab07dab7f115264a4598329fb031e299db0c2bcb8a7526ff93e4f875f"},"schema_version":"1.0","source":{"id":"2411.07760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07760","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07760v1","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07760","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_12","alias_value":"NBG4WUTFLMQ5","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_16","alias_value":"NBG4WUTFLMQ5A6QQ","created_at":"2026-07-05T09:34:28Z"},{"alias_kind":"pith_short_8","alias_value":"NBG4WUTF","created_at":"2026-07-05T09:34:28Z"}],"graph_snapshots":[{"event_id":"sha256:5cb3f34c6afc54b9fcd3285d46881aa95dd7621c74c86c4d776196269231e638","target":"graph","created_at":"2026-07-05T09:34:28Z","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/2411.07760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (RL) has emerged as a powerful alternative to imitation learning for behavior modeling in various domains, particularly in complex navigation tasks. An existing challenge with Offline RL is the signal-to-noise ratio, i.e. how to mitigate incorrect policy updates due to errors in value estimates. Towards this, multiple works have demonstrated the advantage of hierarchical offline RL methods, which decouples high-level path planning from low-level path following. In this work, we present a novel hierarchical transformer-based approach leveraging a learned quantizer","authors_text":"Alexi Canesse, Ludovic Denoyer, Mathieu Petitbois, R\\'emy Portelas, Sylvain Lamprier","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:49:41Z","title":"Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07760","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":"sha256:6780e61be9497bd3b494df56e885d6facc1af8e885cdebf3fc26dd1a8ace0be8","target":"record","created_at":"2026-07-05T09:34:28Z","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":"862195dc10d6e53437e0beab27bf07d396e2ab06ace02e85d1cd55a4845ecbd3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T12:49:41Z","title_canon_sha256":"18438f0ab07dab7f115264a4598329fb031e299db0c2bcb8a7526ff93e4f875f"},"schema_version":"1.0","source":{"id":"2411.07760","kind":"arxiv","version":1}},"canonical_sha256":"684dcb52655b21d07a10316a74438354f1e66c5bec5c5b84ed878a545a27b62e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"684dcb52655b21d07a10316a74438354f1e66c5bec5c5b84ed878a545a27b62e","first_computed_at":"2026-07-05T09:34:28.389565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:28.389565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y5xjl7GxHOaRB58XyrlM+dxYTDrbQ2+sGLoIQW5yRINkMwa0rlUbKhQ0VonT6Ioy4UftE4lzUWm9DmIoAsZBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:28.389938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6780e61be9497bd3b494df56e885d6facc1af8e885cdebf3fc26dd1a8ace0be8","sha256:5cb3f34c6afc54b9fcd3285d46881aa95dd7621c74c86c4d776196269231e638"],"state_sha256":"57a18eede628e544834018fb3237cd38fdd6520f4a90b5c89353cfa0c902c717"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOD0LKTlDCpjbPEgxTznAxJaqDRVuX3K+IN2i9TXqiJU64Up0SE3267/vUYlcQqNK5asaXQUi3F3kGTJxd7ZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T00:04:02.065112Z","bundle_sha256":"e24039e4eb028b35836edbeeb6d2eb8e8e939b0904d0ee7c396f07a1a3feae1f"}}