{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4N4U56Z7VIC3247FPFXWEXE7QH","short_pith_number":"pith:4N4U56Z7","canonical_record":{"source":{"id":"2108.13643","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T07:03:06Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"4c3aa181c33f75f58123423ce8b744443e633636fe7c542d5c95a1e3749bbb81","abstract_canon_sha256":"1d298384456b3aa2240c4e34ca971b8bbe5e350cd37beb2969ac6c66ba5b2e5c"},"schema_version":"1.0"},"canonical_sha256":"e3794efb3faa05bd73e5796f625c9f81c1028e6c14e38268a93f06d3d2e06666","source":{"kind":"arxiv","id":"2108.13643","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13643","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13643v4","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13643","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"4N4U56Z7VIC3","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"4N4U56Z7VIC3247F","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"4N4U56Z7","created_at":"2026-07-05T03:53:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4N4U56Z7VIC3247FPFXWEXE7QH","target":"record","payload":{"canonical_record":{"source":{"id":"2108.13643","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T07:03:06Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"4c3aa181c33f75f58123423ce8b744443e633636fe7c542d5c95a1e3749bbb81","abstract_canon_sha256":"1d298384456b3aa2240c4e34ca971b8bbe5e350cd37beb2969ac6c66ba5b2e5c"},"schema_version":"1.0"},"canonical_sha256":"e3794efb3faa05bd73e5796f625c9f81c1028e6c14e38268a93f06d3d2e06666","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:03.535081Z","signature_b64":"NStvwrwXJKF+waA4Nb+32DbOg7HFOcftoyY886GLNdac7V0kpKfL4P8ojLj9oGndzIbN95kb00gvhOGYNtI2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3794efb3faa05bd73e5796f625c9f81c1028e6c14e38268a93f06d3d2e06666","last_reissued_at":"2026-07-05T03:53:03.534583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:03.534583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.13643","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2WEilCcyttkx5C3uCjDI8LL6AivjHcpayOlZ7Y6q31i8jNO6H7XybgGGWihKJVWkAUg+FYrz12FuBbVzDl2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:49:08.769937Z"},"content_sha256":"f0df8c4cc528cb8e52cfb24146118464d9e128afd9b9227c8ff79ee63dae9c46","schema_version":"1.0","event_id":"sha256:f0df8c4cc528cb8e52cfb24146118464d9e128afd9b9227c8ff79ee63dae9c46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4N4U56Z7VIC3247FPFXWEXE7QH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Dweep Trivedi, Jesse Zhang, Joseph J. Lim, Shao-Hua Sun","submitted_at":"2021-08-31T07:03:06Z","abstract_excerpt":"Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty generalizing to novel scenarios. To address these issues, prior works explore learning programmatic policies that are more interpretable and structured for generalization. Yet, these works either employ limited policy representations (e.g. decision trees, state machines, or predefined program templates) or require stronger supervision (e.g. input/output state pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13643","kind":"arxiv","version":4},"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/2108.13643/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":"2026-07-05T03:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yK/xvL3FXWRM5lDzryiOtWEvE8R1SvHbZAdbpZzR0aLfsXQOwo6bRNppqZW+9cHUTBOVMwz/vEU8FS1Rzw25Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:49:08.770442Z"},"content_sha256":"82e594ff2e13c091438018bfabce5e119bf6c7eb18b2284c2dccf68ced5a2d47","schema_version":"1.0","event_id":"sha256:82e594ff2e13c091438018bfabce5e119bf6c7eb18b2284c2dccf68ced5a2d47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4N4U56Z7VIC3247FPFXWEXE7QH/bundle.json","state_url":"https://pith.science/pith/4N4U56Z7VIC3247FPFXWEXE7QH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4N4U56Z7VIC3247FPFXWEXE7QH/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":"2026-08-17T14:49:08Z","links":{"resolver":"https://pith.science/pith/4N4U56Z7VIC3247FPFXWEXE7QH","bundle":"https://pith.science/pith/4N4U56Z7VIC3247FPFXWEXE7QH/bundle.json","state":"https://pith.science/pith/4N4U56Z7VIC3247FPFXWEXE7QH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4N4U56Z7VIC3247FPFXWEXE7QH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4N4U56Z7VIC3247FPFXWEXE7QH","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":"1d298384456b3aa2240c4e34ca971b8bbe5e350cd37beb2969ac6c66ba5b2e5c","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T07:03:06Z","title_canon_sha256":"4c3aa181c33f75f58123423ce8b744443e633636fe7c542d5c95a1e3749bbb81"},"schema_version":"1.0","source":{"id":"2108.13643","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13643","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13643v4","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13643","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"4N4U56Z7VIC3","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"4N4U56Z7VIC3247F","created_at":"2026-07-05T03:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"4N4U56Z7","created_at":"2026-07-05T03:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:82e594ff2e13c091438018bfabce5e119bf6c7eb18b2284c2dccf68ced5a2d47","target":"graph","created_at":"2026-07-05T03:53:03Z","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/2108.13643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty generalizing to novel scenarios. To address these issues, prior works explore learning programmatic policies that are more interpretable and structured for generalization. Yet, these works either employ limited policy representations (e.g. decision trees, state machines, or predefined program templates) or require stronger supervision (e.g. input/output state pa","authors_text":"Dweep Trivedi, Jesse Zhang, Joseph J. Lim, Shao-Hua Sun","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T07:03:06Z","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13643","kind":"arxiv","version":4},"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:f0df8c4cc528cb8e52cfb24146118464d9e128afd9b9227c8ff79ee63dae9c46","target":"record","created_at":"2026-07-05T03:53:03Z","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":"1d298384456b3aa2240c4e34ca971b8bbe5e350cd37beb2969ac6c66ba5b2e5c","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T07:03:06Z","title_canon_sha256":"4c3aa181c33f75f58123423ce8b744443e633636fe7c542d5c95a1e3749bbb81"},"schema_version":"1.0","source":{"id":"2108.13643","kind":"arxiv","version":4}},"canonical_sha256":"e3794efb3faa05bd73e5796f625c9f81c1028e6c14e38268a93f06d3d2e06666","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3794efb3faa05bd73e5796f625c9f81c1028e6c14e38268a93f06d3d2e06666","first_computed_at":"2026-07-05T03:53:03.534583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:03.534583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NStvwrwXJKF+waA4Nb+32DbOg7HFOcftoyY886GLNdac7V0kpKfL4P8ojLj9oGndzIbN95kb00gvhOGYNtI2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:03.535081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13643","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0df8c4cc528cb8e52cfb24146118464d9e128afd9b9227c8ff79ee63dae9c46","sha256:82e594ff2e13c091438018bfabce5e119bf6c7eb18b2284c2dccf68ced5a2d47"],"state_sha256":"727e6ad256644187322fe95349aa390bb22df070b4a170623b6c10f68effdc29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+kIz5esGps/+Yy7T5nNCQk5rRkj0beybH3MjHn3tMIAgVDcsOLbAjrxXoRDZ8Jh2Jus/n+L3d3daUEspCA7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:49:08.775233Z","bundle_sha256":"f66b07203a88e630cede5d7d58bdba673d994a5dd4396786b3d6cb7c589b4f85"}}