{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JCFK435FZAYCKL6WFYPRYQSIPU","short_pith_number":"pith:JCFK435F","canonical_record":{"source":{"id":"2110.14350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T11:04:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59acdbfce39460719d105fb81f37828c6a64be479077c7fdeafcefcb05301b16","abstract_canon_sha256":"c4cace49eb5e4ff1a4f6ae422ea03b94bbe0e264060685ba942a3f7c2119b261"},"schema_version":"1.0"},"canonical_sha256":"488aae6fa5c830252fd62e1f1c42487d0fee68566dc7aea5f5fc456a352ccbe0","source":{"kind":"arxiv","id":"2110.14350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14350","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14350v1","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14350","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"JCFK435FZAYC","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"JCFK435FZAYCKL6W","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"JCFK435F","created_at":"2026-07-05T03:26:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JCFK435FZAYCKL6WFYPRYQSIPU","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T11:04:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59acdbfce39460719d105fb81f37828c6a64be479077c7fdeafcefcb05301b16","abstract_canon_sha256":"c4cace49eb5e4ff1a4f6ae422ea03b94bbe0e264060685ba942a3f7c2119b261"},"schema_version":"1.0"},"canonical_sha256":"488aae6fa5c830252fd62e1f1c42487d0fee68566dc7aea5f5fc456a352ccbe0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:26.797304Z","signature_b64":"dGGeqP2eDie6uavgD6i5toX5CmlY8pseeV7Zd+LYUKdFxbbT8gug3WEzEOuvofxSxMBO9W7E4Fdxsz8Qcsa6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488aae6fa5c830252fd62e1f1c42487d0fee68566dc7aea5f5fc456a352ccbe0","last_reissued_at":"2026-07-05T03:26:26.796946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:26.796946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14350","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":"2026-07-05T03:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXM9/2j2L3SbEDh+UbNXFh2pKnhwLBI0h9VzU6qc4Hs6d82BvUjYSQnCNM4lYOiQEa6yux4hM2ONggAEd8TJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:48:04.493249Z"},"content_sha256":"88f1c4d650eddb4bdb95455f7dfb0e1ad73aecea2fda8465cfda50e84c7e45a2","schema_version":"1.0","event_id":"sha256:88f1c4d650eddb4bdb95455f7dfb0e1ad73aecea2fda8465cfda50e84c7e45a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JCFK435FZAYCKL6WFYPRYQSIPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dietrich Klakow, Florian Dietz","submitted_at":"2021-10-27T11:04:23Z","abstract_excerpt":"Even though most interfaces in the real world are discrete, no efficient way exists to train neural networks to make use of them, yet. We enhance an Interaction Network (a Reinforcement Learning architecture) with discrete interfaces and train it on the generalized Dyck language. This task requires an understanding of hierarchical structures to solve, and has long proven difficult for neural networks. We provide the first solution based on learning to use discrete data structures. We encountered unexpected anomalous behavior during training, and utilized pre-training based on execution traces "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14350","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/2110.14350/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":"2026-07-05T03:26:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YWSHfp1uHeR0yjwHANlmbaANV/kSshgkXTo0NM0G3F8jcePLP9Rmq7CKxfww0AlFGTYugzVNTW2OuodsurUSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:48:04.493636Z"},"content_sha256":"f68613a1c0f4ce3c4648aa92b9fc72f4ceb9f94fa9f70e9a23a4d9a5cd34cc72","schema_version":"1.0","event_id":"sha256:f68613a1c0f4ce3c4648aa92b9fc72f4ceb9f94fa9f70e9a23a4d9a5cd34cc72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCFK435FZAYCKL6WFYPRYQSIPU/bundle.json","state_url":"https://pith.science/pith/JCFK435FZAYCKL6WFYPRYQSIPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCFK435FZAYCKL6WFYPRYQSIPU/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":"2026-07-07T15:48:04Z","links":{"resolver":"https://pith.science/pith/JCFK435FZAYCKL6WFYPRYQSIPU","bundle":"https://pith.science/pith/JCFK435FZAYCKL6WFYPRYQSIPU/bundle.json","state":"https://pith.science/pith/JCFK435FZAYCKL6WFYPRYQSIPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCFK435FZAYCKL6WFYPRYQSIPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JCFK435FZAYCKL6WFYPRYQSIPU","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":"c4cace49eb5e4ff1a4f6ae422ea03b94bbe0e264060685ba942a3f7c2119b261","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T11:04:23Z","title_canon_sha256":"59acdbfce39460719d105fb81f37828c6a64be479077c7fdeafcefcb05301b16"},"schema_version":"1.0","source":{"id":"2110.14350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14350","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14350v1","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14350","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"JCFK435FZAYC","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"JCFK435FZAYCKL6W","created_at":"2026-07-05T03:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"JCFK435F","created_at":"2026-07-05T03:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:f68613a1c0f4ce3c4648aa92b9fc72f4ceb9f94fa9f70e9a23a4d9a5cd34cc72","target":"graph","created_at":"2026-07-05T03:26:26Z","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/2110.14350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Even though most interfaces in the real world are discrete, no efficient way exists to train neural networks to make use of them, yet. We enhance an Interaction Network (a Reinforcement Learning architecture) with discrete interfaces and train it on the generalized Dyck language. This task requires an understanding of hierarchical structures to solve, and has long proven difficult for neural networks. We provide the first solution based on learning to use discrete data structures. We encountered unexpected anomalous behavior during training, and utilized pre-training based on execution traces ","authors_text":"Dietrich Klakow, Florian Dietz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T11:04:23Z","title":"Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14350","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":"sha256:88f1c4d650eddb4bdb95455f7dfb0e1ad73aecea2fda8465cfda50e84c7e45a2","target":"record","created_at":"2026-07-05T03:26:26Z","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":"c4cace49eb5e4ff1a4f6ae422ea03b94bbe0e264060685ba942a3f7c2119b261","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T11:04:23Z","title_canon_sha256":"59acdbfce39460719d105fb81f37828c6a64be479077c7fdeafcefcb05301b16"},"schema_version":"1.0","source":{"id":"2110.14350","kind":"arxiv","version":1}},"canonical_sha256":"488aae6fa5c830252fd62e1f1c42487d0fee68566dc7aea5f5fc456a352ccbe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"488aae6fa5c830252fd62e1f1c42487d0fee68566dc7aea5f5fc456a352ccbe0","first_computed_at":"2026-07-05T03:26:26.796946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:26.796946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dGGeqP2eDie6uavgD6i5toX5CmlY8pseeV7Zd+LYUKdFxbbT8gug3WEzEOuvofxSxMBO9W7E4Fdxsz8Qcsa6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:26.797304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88f1c4d650eddb4bdb95455f7dfb0e1ad73aecea2fda8465cfda50e84c7e45a2","sha256:f68613a1c0f4ce3c4648aa92b9fc72f4ceb9f94fa9f70e9a23a4d9a5cd34cc72"],"state_sha256":"e126290ffbfa0c25b34d5f4ece2d04b101715ec7ab6e2f08d48b6abced880501"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vT5djc2+KrlKy87e88o5VCsdo02jc00dQCtfgHsVx+0bn/Ei8yrDjAAJthCHCLUMSYQX6CAdWmVt6qT5TVN8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:48:04.495572Z","bundle_sha256":"6a9fef478f9ce706d42ba0a4d21608f656075ec6fbec7323e4d39baf3ebc3541"}}