{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XKCDJQ6WZVLDAVBZ6IHT2B5QOK","short_pith_number":"pith:XKCDJQ6W","canonical_record":{"source":{"id":"1801.03526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-10T19:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"788602e7a04557785f8d6c7af3ee6923a473907de4aae1ccb8b7c56942dc1b18","abstract_canon_sha256":"0aa43cf2b5b823527a916bc1cd8603c5734585e7b483d636356888b6c71c3ade"},"schema_version":"1.0"},"canonical_sha256":"ba8434c3d6cd56305439f20f3d07b0728017fe08e859e4f531cc5562e3c003db","source":{"kind":"arxiv","id":"1801.03526","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03526","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03526v2","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03526","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"XKCDJQ6WZVLD","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKCDJQ6WZVLDAVBZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKCDJQ6W","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XKCDJQ6WZVLDAVBZ6IHT2B5QOK","target":"record","payload":{"canonical_record":{"source":{"id":"1801.03526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-10T19:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"788602e7a04557785f8d6c7af3ee6923a473907de4aae1ccb8b7c56942dc1b18","abstract_canon_sha256":"0aa43cf2b5b823527a916bc1cd8603c5734585e7b483d636356888b6c71c3ade"},"schema_version":"1.0"},"canonical_sha256":"ba8434c3d6cd56305439f20f3d07b0728017fe08e859e4f531cc5562e3c003db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:16.147429Z","signature_b64":"imu34xvYTwscvdEif9qyLWzCwyovYBQE54uyXGQXtTQka5XGseqA4ix2vRfPD6SWIIJ9QCsVqbOyOsiXt0ezCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8434c3d6cd56305439f20f3d07b0728017fe08e859e4f531cc5562e3c003db","last_reissued_at":"2026-05-18T00:20:16.146766Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:16.146766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.03526","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":"2026-05-18T00:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/KUAeOQDzS8WejYDdC0MVykkWwRLFVhbQwWcRJm4igNsbfRUkmKMTZz2qL04f77UiGiH+WWP0N6WuL4o8PVWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:05:56.770900Z"},"content_sha256":"722c07886b74d68bb4c4db0cbbb7fc93531cb43d504f77a417c20c118f6ee6a0","schema_version":"1.0","event_id":"sha256:722c07886b74d68bb4c4db0cbbb7fc93531cb43d504f77a417c20c118f6ee6a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XKCDJQ6WZVLDAVBZ6IHT2B5QOK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Program Synthesis with Priority Queue Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel A. Abolafia, Jonathan Shen, Mohammad Norouzi, Quoc V. Le, Rui Zhao","submitted_at":"2018-01-10T19:35:25Z","abstract_excerpt":"We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. We employ an iterative optimization scheme, where we train an RNN on a dataset of K best programs from a priority queue of the generated programs so far. Then, we synthesize new programs and add them to the priority queue by sampling from the RNN. We benchmark our algorithm, called priority queue training (or PQT), against genetic algorithm and reinforcement learning baselines on a simple but expressive Turing complete programming "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03526","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":""},"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":"2026-05-18T00:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+YbU/f8LOW+ezhhG0UljUhAZ1vU4DlioqB5415XsRrYSdYnpCScF3h7IgWiOTIwMVW8pzM/aT93/YB8CQUDIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:05:56.771243Z"},"content_sha256":"91a9aa62ad2cd65aea3f978817a308ed0bb4fb58c0d39859d9f1a884fcdcf88f","schema_version":"1.0","event_id":"sha256:91a9aa62ad2cd65aea3f978817a308ed0bb4fb58c0d39859d9f1a884fcdcf88f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/bundle.json","state_url":"https://pith.science/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/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":"2026-05-20T12:05:56Z","links":{"resolver":"https://pith.science/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK","bundle":"https://pith.science/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/bundle.json","state":"https://pith.science/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKCDJQ6WZVLDAVBZ6IHT2B5QOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XKCDJQ6WZVLDAVBZ6IHT2B5QOK","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":"0aa43cf2b5b823527a916bc1cd8603c5734585e7b483d636356888b6c71c3ade","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-10T19:35:25Z","title_canon_sha256":"788602e7a04557785f8d6c7af3ee6923a473907de4aae1ccb8b7c56942dc1b18"},"schema_version":"1.0","source":{"id":"1801.03526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03526","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03526v2","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03526","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"XKCDJQ6WZVLD","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKCDJQ6WZVLDAVBZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKCDJQ6W","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:91a9aa62ad2cd65aea3f978817a308ed0bb4fb58c0d39859d9f1a884fcdcf88f","target":"graph","created_at":"2026-05-18T00:20:16Z","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"},"paper":{"abstract_excerpt":"We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. We employ an iterative optimization scheme, where we train an RNN on a dataset of K best programs from a priority queue of the generated programs so far. Then, we synthesize new programs and add them to the priority queue by sampling from the RNN. We benchmark our algorithm, called priority queue training (or PQT), against genetic algorithm and reinforcement learning baselines on a simple but expressive Turing complete programming ","authors_text":"Daniel A. Abolafia, Jonathan Shen, Mohammad Norouzi, Quoc V. Le, Rui Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-10T19:35:25Z","title":"Neural Program Synthesis with Priority Queue Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03526","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":"sha256:722c07886b74d68bb4c4db0cbbb7fc93531cb43d504f77a417c20c118f6ee6a0","target":"record","created_at":"2026-05-18T00:20:16Z","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":"0aa43cf2b5b823527a916bc1cd8603c5734585e7b483d636356888b6c71c3ade","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-10T19:35:25Z","title_canon_sha256":"788602e7a04557785f8d6c7af3ee6923a473907de4aae1ccb8b7c56942dc1b18"},"schema_version":"1.0","source":{"id":"1801.03526","kind":"arxiv","version":2}},"canonical_sha256":"ba8434c3d6cd56305439f20f3d07b0728017fe08e859e4f531cc5562e3c003db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba8434c3d6cd56305439f20f3d07b0728017fe08e859e4f531cc5562e3c003db","first_computed_at":"2026-05-18T00:20:16.146766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:16.146766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"imu34xvYTwscvdEif9qyLWzCwyovYBQE54uyXGQXtTQka5XGseqA4ix2vRfPD6SWIIJ9QCsVqbOyOsiXt0ezCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:16.147429Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.03526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:722c07886b74d68bb4c4db0cbbb7fc93531cb43d504f77a417c20c118f6ee6a0","sha256:91a9aa62ad2cd65aea3f978817a308ed0bb4fb58c0d39859d9f1a884fcdcf88f"],"state_sha256":"9060c38df51b046c5619038e8daeff3c2e4fa977804497fb1a9bdb6ee089e7ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFeFwWzEyeANVpQ/Fy3Ubos9HQhoMJQ5SdsmNjoE+sRGHVG2wVA8/dI0BYKBc56Ty9dOTf6iEWO4wSUFLiDXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T12:05:56.773214Z","bundle_sha256":"b9bf9e53dbbe320cb687f748ed5b2ec4d54b83fad35d8829d16ae9cbe008de51"}}