{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7YAI6QVVIQQZIGJ6OHCCZLWVPM","short_pith_number":"pith:7YAI6QVV","canonical_record":{"source":{"id":"1912.00444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-01T17:08:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"904ebc2d98f578c2754bcc0cb3d7c5d67478e6b00f525e44700394d493cd3457","abstract_canon_sha256":"c3dd053c40d52b8813e6b7504bec8c7fba7150a9c8b171a2d0d0a233709d5fea"},"schema_version":"1.0"},"canonical_sha256":"fe008f42b5442194193e71c42caed57b18ef84cf2130922ea0bf23d275912c67","source":{"kind":"arxiv","id":"1912.00444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00444","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00444v1","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00444","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"7YAI6QVVIQQZ","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"7YAI6QVVIQQZIGJ6","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"7YAI6QVV","created_at":"2026-07-05T00:23:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7YAI6QVVIQQZIGJ6OHCCZLWVPM","target":"record","payload":{"canonical_record":{"source":{"id":"1912.00444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-01T17:08:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"904ebc2d98f578c2754bcc0cb3d7c5d67478e6b00f525e44700394d493cd3457","abstract_canon_sha256":"c3dd053c40d52b8813e6b7504bec8c7fba7150a9c8b171a2d0d0a233709d5fea"},"schema_version":"1.0"},"canonical_sha256":"fe008f42b5442194193e71c42caed57b18ef84cf2130922ea0bf23d275912c67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:13.982915Z","signature_b64":"kxL5gfoP8VxU7C0tGMuLHEicemFfNaVLYBq/7HHUAgArb7YZCXM07VQ2iV5O7/RJTwRX8c3ZgfeHyoR6eUqDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe008f42b5442194193e71c42caed57b18ef84cf2130922ea0bf23d275912c67","last_reissued_at":"2026-07-05T00:23:13.982555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:13.982555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.00444","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":"2026-07-05T00:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMGG5YJM+DM1CuZBQ6PLz3cJC/Ca7rw1PYvTebFEaqVxlIHd7ZWvdJKBVGpoK2+Ptp2ApJu/uwGsI1yzzDR2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:53:15.827686Z"},"content_sha256":"53a1837f5ff80f52748c07ad6fa0f916cbc6cc92e4c6dce92ed6144276f6a798","schema_version":"1.0","event_id":"sha256:53a1837f5ff80f52748c07ad6fa0f916cbc6cc92e4c6dce92ed6144276f6a798"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7YAI6QVVIQQZIGJ6OHCCZLWVPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated curriculum generation for Policy Gradients from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio","submitted_at":"2019-12-01T17:08:34Z","abstract_excerpt":"In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following. We develop a training curriculum that uses a nominal number of expert demonstrations and trains the agent in a manner that draws parallels from one of the ways in which humans learn to perform complex tasks, i.e by starting from the goal and working backwards. We test our method on the BabyAI platform and show an improvement in sample efficiency for some of its tasks compared to a PPO (proximal policy optimization) baseline."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00444","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/1912.00444/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":"2026-07-05T00:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EXG/G2xDWBXKiBEK9ee4G+NVkmhUCyoInLZ32Ib+CJDRvaapdQMxTE309BVFCMAAzxYlcb6buo2pFBqCVjJOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:53:15.828237Z"},"content_sha256":"1a936b4e2689153b3842782ebceb6370787e23e84eed0b5103512006f5491ef6","schema_version":"1.0","event_id":"sha256:1a936b4e2689153b3842782ebceb6370787e23e84eed0b5103512006f5491ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/bundle.json","state_url":"https://pith.science/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/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":"2026-08-04T08:53:15Z","links":{"resolver":"https://pith.science/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM","bundle":"https://pith.science/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/bundle.json","state":"https://pith.science/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YAI6QVVIQQZIGJ6OHCCZLWVPM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7YAI6QVVIQQZIGJ6OHCCZLWVPM","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":"c3dd053c40d52b8813e6b7504bec8c7fba7150a9c8b171a2d0d0a233709d5fea","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-01T17:08:34Z","title_canon_sha256":"904ebc2d98f578c2754bcc0cb3d7c5d67478e6b00f525e44700394d493cd3457"},"schema_version":"1.0","source":{"id":"1912.00444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00444","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00444v1","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00444","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"7YAI6QVVIQQZ","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"7YAI6QVVIQQZIGJ6","created_at":"2026-07-05T00:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"7YAI6QVV","created_at":"2026-07-05T00:23:13Z"}],"graph_snapshots":[{"event_id":"sha256:1a936b4e2689153b3842782ebceb6370787e23e84eed0b5103512006f5491ef6","target":"graph","created_at":"2026-07-05T00:23:13Z","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/1912.00444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following. We develop a training curriculum that uses a nominal number of expert demonstrations and trains the agent in a manner that draws parallels from one of the ways in which humans learn to perform complex tasks, i.e by starting from the goal and working backwards. We test our method on the BabyAI platform and show an improvement in sample efficiency for some of its tasks compared to a PPO (proximal policy optimization) baseline.","authors_text":"Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-01T17:08:34Z","title":"Automated curriculum generation for Policy Gradients from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00444","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":"sha256:53a1837f5ff80f52748c07ad6fa0f916cbc6cc92e4c6dce92ed6144276f6a798","target":"record","created_at":"2026-07-05T00:23:13Z","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":"c3dd053c40d52b8813e6b7504bec8c7fba7150a9c8b171a2d0d0a233709d5fea","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-01T17:08:34Z","title_canon_sha256":"904ebc2d98f578c2754bcc0cb3d7c5d67478e6b00f525e44700394d493cd3457"},"schema_version":"1.0","source":{"id":"1912.00444","kind":"arxiv","version":1}},"canonical_sha256":"fe008f42b5442194193e71c42caed57b18ef84cf2130922ea0bf23d275912c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe008f42b5442194193e71c42caed57b18ef84cf2130922ea0bf23d275912c67","first_computed_at":"2026-07-05T00:23:13.982555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:13.982555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kxL5gfoP8VxU7C0tGMuLHEicemFfNaVLYBq/7HHUAgArb7YZCXM07VQ2iV5O7/RJTwRX8c3ZgfeHyoR6eUqDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:13.982915Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a1837f5ff80f52748c07ad6fa0f916cbc6cc92e4c6dce92ed6144276f6a798","sha256:1a936b4e2689153b3842782ebceb6370787e23e84eed0b5103512006f5491ef6"],"state_sha256":"8c4f34eee54d2ee06b9f6d929aa17128b84192171eead09e6a930a2a363ceaf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WOpNENikdxkCwZf/ShV0wc2sEluQ9hDAPQ0BJA6vJ+QGasGsH96EcJh+In9IBUOx4ExiB+1mIQjY8E9Y4PBRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:53:15.834769Z","bundle_sha256":"b85b5b5f20926040a02e70294cd45b1e23d787614c8d0eb66a7371c28dfe199a"}}