{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6U7TQZ5YDAATFSQ7UOIVVUBWVS","short_pith_number":"pith:6U7TQZ5Y","canonical_record":{"source":{"id":"2007.13363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-27T08:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"9ad7774dae167f4c702d7aed02cb67807c76e46cb9884b348ac22d9bf82a4040","abstract_canon_sha256":"f21052f5edad7cc4b2a7fdb09e795be77c0a1523e165bf5f6ec9a820a7325d7e"},"schema_version":"1.0"},"canonical_sha256":"f53f3867b8180132ca1fa3915ad036aca8a129177079e9f78a654351e7f9022a","source":{"kind":"arxiv","id":"2007.13363","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13363","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13363v2","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13363","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"6U7TQZ5YDAAT","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"6U7TQZ5YDAATFSQ7","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"6U7TQZ5Y","created_at":"2026-07-05T02:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6U7TQZ5YDAATFSQ7UOIVVUBWVS","target":"record","payload":{"canonical_record":{"source":{"id":"2007.13363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-27T08:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"9ad7774dae167f4c702d7aed02cb67807c76e46cb9884b348ac22d9bf82a4040","abstract_canon_sha256":"f21052f5edad7cc4b2a7fdb09e795be77c0a1523e165bf5f6ec9a820a7325d7e"},"schema_version":"1.0"},"canonical_sha256":"f53f3867b8180132ca1fa3915ad036aca8a129177079e9f78a654351e7f9022a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:18.831137Z","signature_b64":"yxdNahJVKsszFOW//NG2pFMGcBSepxpBuqgnTKTBE1SsoduLCN1Xdoym+ZALRATz2+OjvZ7o4AM0plNkSznpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53f3867b8180132ca1fa3915ad036aca8a129177079e9f78a654351e7f9022a","last_reissued_at":"2026-07-05T02:31:18.830746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:18.830746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.13363","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cY5gk2FuZpkPMMwEiBlaAHIZzRyYxY4nByibtHRZgcaYFiJehI+h8HbI2pTvyNi3LKQBmvetm7Zl9prm5bEKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:06:59.478728Z"},"content_sha256":"1299a0c92df508ff3902e0d62088f3ba56d4790ee068a093330a81fbfce4e176","schema_version":"1.0","event_id":"sha256:1299a0c92df508ff3902e0d62088f3ba56d4790ee068a093330a81fbfce4e176"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6U7TQZ5YDAATFSQ7UOIVVUBWVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Compositional Neural Programs for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandre Laterre, Feryal Behbahani, Karim Beguir, Nando de Freitas, Nicolas Perrin, Olivier Sigaud, Thomas Pierrot","submitted_at":"2020-07-27T08:27:14Z","abstract_excerpt":"We propose a novel solution to challenging sparse-reward, continuous control problems that require hierarchical planning at multiple levels of abstraction. Our solution, dubbed AlphaNPI-X, involves three separate stages of learning. First, we use off-policy reinforcement learning algorithms with experience replay to learn a set of atomic goal-conditioned policies, which can be easily repurposed for many tasks. Second, we learn self-models describing the effect of the atomic policies on the environment. Third, the self-models are harnessed to learn recursive compositional programs with multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13363","kind":"arxiv","version":2},"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/2007.13363/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":"2026-07-05T02:31:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTQSj1p5I0TM0/Zwp6NrSaZxuWdV1P73gO5xJrJi6HbqLNKRQ7cO5kd7av2TyQVqLcDKSKqnm21tOWgo20bDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:06:59.479050Z"},"content_sha256":"6d9323aa2d467feb427fe3e6dafee31af9cf67a3a67dc66fcfe4970e95c5b290","schema_version":"1.0","event_id":"sha256:6d9323aa2d467feb427fe3e6dafee31af9cf67a3a67dc66fcfe4970e95c5b290"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/bundle.json","state_url":"https://pith.science/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/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":"2026-08-14T08:06:59Z","links":{"resolver":"https://pith.science/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS","bundle":"https://pith.science/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/bundle.json","state":"https://pith.science/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U7TQZ5YDAATFSQ7UOIVVUBWVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6U7TQZ5YDAATFSQ7UOIVVUBWVS","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":"f21052f5edad7cc4b2a7fdb09e795be77c0a1523e165bf5f6ec9a820a7325d7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-27T08:27:14Z","title_canon_sha256":"9ad7774dae167f4c702d7aed02cb67807c76e46cb9884b348ac22d9bf82a4040"},"schema_version":"1.0","source":{"id":"2007.13363","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13363","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13363v2","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13363","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"6U7TQZ5YDAAT","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"6U7TQZ5YDAATFSQ7","created_at":"2026-07-05T02:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"6U7TQZ5Y","created_at":"2026-07-05T02:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:6d9323aa2d467feb427fe3e6dafee31af9cf67a3a67dc66fcfe4970e95c5b290","target":"graph","created_at":"2026-07-05T02:31:18Z","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/2007.13363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel solution to challenging sparse-reward, continuous control problems that require hierarchical planning at multiple levels of abstraction. Our solution, dubbed AlphaNPI-X, involves three separate stages of learning. First, we use off-policy reinforcement learning algorithms with experience replay to learn a set of atomic goal-conditioned policies, which can be easily repurposed for many tasks. Second, we learn self-models describing the effect of the atomic policies on the environment. Third, the self-models are harnessed to learn recursive compositional programs with multiple","authors_text":"Alexandre Laterre, Feryal Behbahani, Karim Beguir, Nando de Freitas, Nicolas Perrin, Olivier Sigaud, Thomas Pierrot","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-27T08:27:14Z","title":"Learning Compositional Neural Programs for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13363","kind":"arxiv","version":2},"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":"sha256:1299a0c92df508ff3902e0d62088f3ba56d4790ee068a093330a81fbfce4e176","target":"record","created_at":"2026-07-05T02:31:18Z","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":"f21052f5edad7cc4b2a7fdb09e795be77c0a1523e165bf5f6ec9a820a7325d7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-27T08:27:14Z","title_canon_sha256":"9ad7774dae167f4c702d7aed02cb67807c76e46cb9884b348ac22d9bf82a4040"},"schema_version":"1.0","source":{"id":"2007.13363","kind":"arxiv","version":2}},"canonical_sha256":"f53f3867b8180132ca1fa3915ad036aca8a129177079e9f78a654351e7f9022a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f53f3867b8180132ca1fa3915ad036aca8a129177079e9f78a654351e7f9022a","first_computed_at":"2026-07-05T02:31:18.830746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:18.830746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yxdNahJVKsszFOW//NG2pFMGcBSepxpBuqgnTKTBE1SsoduLCN1Xdoym+ZALRATz2+OjvZ7o4AM0plNkSznpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:18.831137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.13363","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1299a0c92df508ff3902e0d62088f3ba56d4790ee068a093330a81fbfce4e176","sha256:6d9323aa2d467feb427fe3e6dafee31af9cf67a3a67dc66fcfe4970e95c5b290"],"state_sha256":"e9ebb4d9e2bf4bf2adc38d7fd73896458b79cc276cfbeb55bdbe8fb5a489d4c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bMp4wnP9fTD5w5wYc9K+LcqBpE1VtE7hMxhSboEPSO7A40MLZzSJn34BGAkybr7nykvMk5O6rr+WvUU0++NBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:06:59.481902Z","bundle_sha256":"57e5896d51d6ad2557f9b8c4d0a35bd7a97f95d5a84afaea01c5ffe1939e9b43"}}