{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WTNT65PGPOBMTSJSKH4VMIPV3K","short_pith_number":"pith:WTNT65PG","canonical_record":{"source":{"id":"2205.05588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-11T16:00:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cde6aef70aee371599c7df02449b6cb7742ec8b43008ebe7388e0c28caeb7d78","abstract_canon_sha256":"baaf1dbd81cf407ef94d0e5951487d131acafddfbb74016d35fa8fbd9a9c4884"},"schema_version":"1.0"},"canonical_sha256":"b4db3f75e67b82c9c93251f95621f5daac2c0dec16776d1b5a934eb854c5c842","source":{"kind":"arxiv","id":"2205.05588","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05588","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05588v1","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05588","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"WTNT65PGPOBM","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"WTNT65PGPOBMTSJS","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"WTNT65PG","created_at":"2026-07-05T04:22:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WTNT65PGPOBMTSJSKH4VMIPV3K","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-11T16:00:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cde6aef70aee371599c7df02449b6cb7742ec8b43008ebe7388e0c28caeb7d78","abstract_canon_sha256":"baaf1dbd81cf407ef94d0e5951487d131acafddfbb74016d35fa8fbd9a9c4884"},"schema_version":"1.0"},"canonical_sha256":"b4db3f75e67b82c9c93251f95621f5daac2c0dec16776d1b5a934eb854c5c842","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:27.446412Z","signature_b64":"3PVu94nHmvZQKterTNHU8moCyX96BUUdglSBFMw6OytfjUsT///rnQFEjS/ALC6onWsXCpGHBCQqI/OIhNp/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4db3f75e67b82c9c93251f95621f5daac2c0dec16776d1b5a934eb854c5c842","last_reissued_at":"2026-07-05T04:22:27.445839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:27.445839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05588","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":"2026-07-05T04:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hu8kLvXQAw+MDyxg3FzHwKqxpmPq2rL/9AP4JckG6tfEVKjcVvXjs4J7niD7bBCRU5nVE4FqPepFC+aUfyaICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T22:01:41.531418Z"},"content_sha256":"a886a41c591fa0b282e17c9324e8bcbc05f24aff9c979beb26ef533a54bb2f64","schema_version":"1.0","event_id":"sha256:a886a41c591fa0b282e17c9324e8bcbc05f24aff9c979beb26ef533a54bb2f64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WTNT65PGPOBMTSJSKH4VMIPV3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing the Action-Generalization Gap in Deep Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Cameron Allen, George Konidaris, Kavosh Asadi, Zhiyuan Zhou","submitted_at":"2022-05-11T16:00:46Z","abstract_excerpt":"We study the action generalization ability of deep Q-learning in discrete action spaces. Generalization is crucial for efficient reinforcement learning (RL) because it allows agents to use knowledge learned from past experiences on new tasks. But while function approximation provides deep RL agents with a natural way to generalize over state inputs, the same generalization mechanism does not apply to discrete action outputs. And yet, surprisingly, our experiments indicate that Deep Q-Networks (DQN), which use exactly this type of function approximator, are still able to achieve modest action g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05588","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/2205.05588/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":"2026-07-05T04:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDooyTJM2Iwp3WCP0/wyhzMQln766O4KRM3SUBxqCMXtSZR+BC/FyTTXlSX2TEaIq7mxKkmeYscSJTnoEfcwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T22:01:41.531802Z"},"content_sha256":"232101e71e6b9997924b30b3614d9e73c9a768f0bf8a751bf2b21c2544943f9e","schema_version":"1.0","event_id":"sha256:232101e71e6b9997924b30b3614d9e73c9a768f0bf8a751bf2b21c2544943f9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/bundle.json","state_url":"https://pith.science/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/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":"2026-07-10T22:01:41Z","links":{"resolver":"https://pith.science/pith/WTNT65PGPOBMTSJSKH4VMIPV3K","bundle":"https://pith.science/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/bundle.json","state":"https://pith.science/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTNT65PGPOBMTSJSKH4VMIPV3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WTNT65PGPOBMTSJSKH4VMIPV3K","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":"baaf1dbd81cf407ef94d0e5951487d131acafddfbb74016d35fa8fbd9a9c4884","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-11T16:00:46Z","title_canon_sha256":"cde6aef70aee371599c7df02449b6cb7742ec8b43008ebe7388e0c28caeb7d78"},"schema_version":"1.0","source":{"id":"2205.05588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05588","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05588v1","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05588","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"WTNT65PGPOBM","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"WTNT65PGPOBMTSJS","created_at":"2026-07-05T04:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"WTNT65PG","created_at":"2026-07-05T04:22:27Z"}],"graph_snapshots":[{"event_id":"sha256:232101e71e6b9997924b30b3614d9e73c9a768f0bf8a751bf2b21c2544943f9e","target":"graph","created_at":"2026-07-05T04:22:27Z","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/2205.05588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the action generalization ability of deep Q-learning in discrete action spaces. Generalization is crucial for efficient reinforcement learning (RL) because it allows agents to use knowledge learned from past experiences on new tasks. But while function approximation provides deep RL agents with a natural way to generalize over state inputs, the same generalization mechanism does not apply to discrete action outputs. And yet, surprisingly, our experiments indicate that Deep Q-Networks (DQN), which use exactly this type of function approximator, are still able to achieve modest action g","authors_text":"Cameron Allen, George Konidaris, Kavosh Asadi, Zhiyuan Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-11T16:00:46Z","title":"Characterizing the Action-Generalization Gap in Deep Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05588","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:a886a41c591fa0b282e17c9324e8bcbc05f24aff9c979beb26ef533a54bb2f64","target":"record","created_at":"2026-07-05T04:22:27Z","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":"baaf1dbd81cf407ef94d0e5951487d131acafddfbb74016d35fa8fbd9a9c4884","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-11T16:00:46Z","title_canon_sha256":"cde6aef70aee371599c7df02449b6cb7742ec8b43008ebe7388e0c28caeb7d78"},"schema_version":"1.0","source":{"id":"2205.05588","kind":"arxiv","version":1}},"canonical_sha256":"b4db3f75e67b82c9c93251f95621f5daac2c0dec16776d1b5a934eb854c5c842","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4db3f75e67b82c9c93251f95621f5daac2c0dec16776d1b5a934eb854c5c842","first_computed_at":"2026-07-05T04:22:27.445839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:27.445839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3PVu94nHmvZQKterTNHU8moCyX96BUUdglSBFMw6OytfjUsT///rnQFEjS/ALC6onWsXCpGHBCQqI/OIhNp/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:27.446412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a886a41c591fa0b282e17c9324e8bcbc05f24aff9c979beb26ef533a54bb2f64","sha256:232101e71e6b9997924b30b3614d9e73c9a768f0bf8a751bf2b21c2544943f9e"],"state_sha256":"5616a10d2a9eb029424265f0965cfbc8dfc69e7ccc0a4660d782be228eddc571"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glyP3k41KIbd3Az2mfL4zBKM6DfWLnTKm/21/MzmP6elSYs22GrntxC0ec9fdo5VZ4uJ3+NxG9Y5qpt2y+ViCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T22:01:41.534239Z","bundle_sha256":"ce18a672eda8ba82f2dbccf41170dd6a6018d03472ee410737a29df2e2ae1466"}}