{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TMJM3Q64RRNWJMBL663LGSC3JD","short_pith_number":"pith:TMJM3Q64","canonical_record":{"source":{"id":"2007.03629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T17:03:02Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"d821ca661d57f7f2882c9e4891b65bbc8ee00056009cc76770188fa658b957c1","abstract_canon_sha256":"e7b1707735ce2764fc4983c0d09022fb21f1cf66b830ec1e17ef434bfd604393"},"schema_version":"1.0"},"canonical_sha256":"9b12cdc3dc8c5b64b02bf7b6b3485b48c0a4926ceca056819fb7c2cd4a051e12","source":{"kind":"arxiv","id":"2007.03629","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03629","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03629v2","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03629","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"TMJM3Q64RRNW","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"TMJM3Q64RRNWJMBL","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"TMJM3Q64","created_at":"2026-07-05T01:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TMJM3Q64RRNWJMBL663LGSC3JD","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T17:03:02Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"d821ca661d57f7f2882c9e4891b65bbc8ee00056009cc76770188fa658b957c1","abstract_canon_sha256":"e7b1707735ce2764fc4983c0d09022fb21f1cf66b830ec1e17ef434bfd604393"},"schema_version":"1.0"},"canonical_sha256":"9b12cdc3dc8c5b64b02bf7b6b3485b48c0a4926ceca056819fb7c2cd4a051e12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:19.257605Z","signature_b64":"BNZOIL41TFb06cyhi/unoPsmrwvuZoxbejWhUFIuXJsm+jOyRk/DPc1eh+rhSMH3bRQQ2VWQrEmYff5mwUttBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b12cdc3dc8c5b64b02bf7b6b3485b48c0a4926ceca056819fb7c2cd4a051e12","last_reissued_at":"2026-07-05T01:17:19.257138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:19.257138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03629","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":"2026-07-05T01:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AonGZSy+F7SQvIvVql3y1K2wTSORSqUwMOL+ap3R7yZ1zIH+zi2HK6YML8zDyRImTwu0XNjqAP+87bwHjMR0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:21:14.129535Z"},"content_sha256":"3dca97ad531235048846e02f738df1d0c1b2370b364dc401adf7fc34596111c3","schema_version":"1.0","event_id":"sha256:3dca97ad531235048846e02f738df1d0c1b2370b364dc401adf7fc34596111c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TMJM3Q64RRNWJMBL663LGSC3JD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Strong Generalization and Efficiency in Neural Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Gimeno, Oriol Vinyals, Pushmeet Kohli, Yujia Li","submitted_at":"2020-07-07T17:03:02Z","abstract_excerpt":"We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03629","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/2007.03629/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":"2026-07-05T01:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFKuLwgfRYYhgY5H7wVTGoNG8WICyr19YEEoqFXRd3wdxY5ZlJ+/cg6f4kKe7vk4vBUqh9SdI8guTFc1zbpEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:21:14.130104Z"},"content_sha256":"a3a064f4d3412efb70568895e71b4e6c26ce31b9992640a8dfe481011e14c98c","schema_version":"1.0","event_id":"sha256:a3a064f4d3412efb70568895e71b4e6c26ce31b9992640a8dfe481011e14c98c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMJM3Q64RRNWJMBL663LGSC3JD/bundle.json","state_url":"https://pith.science/pith/TMJM3Q64RRNWJMBL663LGSC3JD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMJM3Q64RRNWJMBL663LGSC3JD/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":"2026-08-11T16:21:14Z","links":{"resolver":"https://pith.science/pith/TMJM3Q64RRNWJMBL663LGSC3JD","bundle":"https://pith.science/pith/TMJM3Q64RRNWJMBL663LGSC3JD/bundle.json","state":"https://pith.science/pith/TMJM3Q64RRNWJMBL663LGSC3JD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMJM3Q64RRNWJMBL663LGSC3JD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TMJM3Q64RRNWJMBL663LGSC3JD","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":"e7b1707735ce2764fc4983c0d09022fb21f1cf66b830ec1e17ef434bfd604393","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T17:03:02Z","title_canon_sha256":"d821ca661d57f7f2882c9e4891b65bbc8ee00056009cc76770188fa658b957c1"},"schema_version":"1.0","source":{"id":"2007.03629","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03629","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03629v2","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03629","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"TMJM3Q64RRNW","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"TMJM3Q64RRNWJMBL","created_at":"2026-07-05T01:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"TMJM3Q64","created_at":"2026-07-05T01:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:a3a064f4d3412efb70568895e71b4e6c26ce31b9992640a8dfe481011e14c98c","target":"graph","created_at":"2026-07-05T01:17:19Z","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/2007.03629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as ","authors_text":"Felix Gimeno, Oriol Vinyals, Pushmeet Kohli, Yujia Li","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T17:03:02Z","title":"Strong Generalization and Efficiency in Neural Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03629","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":"sha256:3dca97ad531235048846e02f738df1d0c1b2370b364dc401adf7fc34596111c3","target":"record","created_at":"2026-07-05T01:17:19Z","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":"e7b1707735ce2764fc4983c0d09022fb21f1cf66b830ec1e17ef434bfd604393","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T17:03:02Z","title_canon_sha256":"d821ca661d57f7f2882c9e4891b65bbc8ee00056009cc76770188fa658b957c1"},"schema_version":"1.0","source":{"id":"2007.03629","kind":"arxiv","version":2}},"canonical_sha256":"9b12cdc3dc8c5b64b02bf7b6b3485b48c0a4926ceca056819fb7c2cd4a051e12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b12cdc3dc8c5b64b02bf7b6b3485b48c0a4926ceca056819fb7c2cd4a051e12","first_computed_at":"2026-07-05T01:17:19.257138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:19.257138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNZOIL41TFb06cyhi/unoPsmrwvuZoxbejWhUFIuXJsm+jOyRk/DPc1eh+rhSMH3bRQQ2VWQrEmYff5mwUttBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:19.257605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03629","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dca97ad531235048846e02f738df1d0c1b2370b364dc401adf7fc34596111c3","sha256:a3a064f4d3412efb70568895e71b4e6c26ce31b9992640a8dfe481011e14c98c"],"state_sha256":"90b9de322c8d98d976c2acb377a91a41ba78f76a5ef53939addc6fa8cf5511be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+shDdgOv5zb2MUwmAffwS8XjA2a63at0Jrcw+C83gQsLMIYcog6RkMGCX20t9ihLmIdN+ffxn4/ZrWH2+2xAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:21:14.134122Z","bundle_sha256":"172c287c2107ec64f63099667b69c01a52ddcd2ae0b00b65c7a3d9f09f7afffd"}}