{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MHNTPSXB4TKI2ANXW35MZJVMKZ","short_pith_number":"pith:MHNTPSXB","canonical_record":{"source":{"id":"2506.16608","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T21:19:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c278b0ac14636c2eda55a20dd71b589ec4e14087415265681e940a02ef0a9c6","abstract_canon_sha256":"d7f143abd25cf5e0badbb4bcd07a4c92f280dd932cf04950b144877a2f63e2aa"},"schema_version":"1.0"},"canonical_sha256":"61db37cae1e4d48d01b7b6facca6ac566443dedd5de3ac8e96e390ce5ec3d537","source":{"kind":"arxiv","id":"2506.16608","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16608","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16608v3","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16608","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"MHNTPSXB4TKI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MHNTPSXB4TKI2ANX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MHNTPSXB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MHNTPSXB4TKI2ANXW35MZJVMKZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16608","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T21:19:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c278b0ac14636c2eda55a20dd71b589ec4e14087415265681e940a02ef0a9c6","abstract_canon_sha256":"d7f143abd25cf5e0badbb4bcd07a4c92f280dd932cf04950b144877a2f63e2aa"},"schema_version":"1.0"},"canonical_sha256":"61db37cae1e4d48d01b7b6facca6ac566443dedd5de3ac8e96e390ce5ec3d537","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:17.909840Z","signature_b64":"Igbs9gNPr7345ryLuOKn/aPQlAIZj/dj05BMxnqBsal+yDONYm5HnUrftmnYYJRP2V5JOFAHr4EjGCdujHVlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61db37cae1e4d48d01b7b6facca6ac566443dedd5de3ac8e96e390ce5ec3d537","last_reissued_at":"2026-05-17T23:39:17.909356Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:17.909356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16608","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcT8O77VxjY5V4KqHsQkzBW1gvjrKkyCt0PB9RiIL+H6JhRBOnCFMOfc2V5Q0xCugKBtkvuVMvx/p1JmSduhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:54:32.409344Z"},"content_sha256":"22b3cfbf411838878ae760275f2e88ad08972292f18dd70df08e9a277d48b1ee","schema_version":"1.0","event_id":"sha256:22b3cfbf411838878ae760275f2e88ad08972292f18dd70df08e9a277d48b1ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MHNTPSXB4TKI2ANXW35MZJVMKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Jiamin He, Martha White","submitted_at":"2025-06-19T21:19:19Z","abstract_excerpt":"We introduce a novel reinforcement learning (RL) framework that treats parameterized action distributions as actions, redefining the boundary between agent and environment. This reparameterization makes the new action space continuous, regardless of the original action type (discrete, continuous, hybrid, etc.). Under this new parameterization, we develop a generalized deterministic policy gradient estimator, Distributions-as-Actions Policy Gradient (DA-PG), which has lower variance than the gradient in the original action space. Although learning the critic over distribution parameters poses n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16608","kind":"arxiv","version":3},"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":"2026-05-17T23:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUNKVAfhJlV0xdFrVfhoplQp4o2stsyFCeac5Y6flLY//1c75XM1deBetwhpyBGgL9ix9A91n5W9ZhrD7zAFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:54:32.409691Z"},"content_sha256":"62412c24fd39835c6ca5fbf50642df47c2f52baf0bf3e9166a055d6012061f15","schema_version":"1.0","event_id":"sha256:62412c24fd39835c6ca5fbf50642df47c2f52baf0bf3e9166a055d6012061f15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/bundle.json","state_url":"https://pith.science/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/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":"2026-05-21T18:54:32Z","links":{"resolver":"https://pith.science/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ","bundle":"https://pith.science/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/bundle.json","state":"https://pith.science/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHNTPSXB4TKI2ANXW35MZJVMKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MHNTPSXB4TKI2ANXW35MZJVMKZ","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":"d7f143abd25cf5e0badbb4bcd07a4c92f280dd932cf04950b144877a2f63e2aa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T21:19:19Z","title_canon_sha256":"0c278b0ac14636c2eda55a20dd71b589ec4e14087415265681e940a02ef0a9c6"},"schema_version":"1.0","source":{"id":"2506.16608","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16608","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16608v3","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16608","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"MHNTPSXB4TKI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MHNTPSXB4TKI2ANX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MHNTPSXB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:62412c24fd39835c6ca5fbf50642df47c2f52baf0bf3e9166a055d6012061f15","target":"graph","created_at":"2026-05-17T23:39:17Z","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 introduce a novel reinforcement learning (RL) framework that treats parameterized action distributions as actions, redefining the boundary between agent and environment. This reparameterization makes the new action space continuous, regardless of the original action type (discrete, continuous, hybrid, etc.). Under this new parameterization, we develop a generalized deterministic policy gradient estimator, Distributions-as-Actions Policy Gradient (DA-PG), which has lower variance than the gradient in the original action space. Although learning the critic over distribution parameters poses n","authors_text":"A. Rupam Mahmood, Jiamin He, Martha White","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T21:19:19Z","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16608","kind":"arxiv","version":3},"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":"sha256:22b3cfbf411838878ae760275f2e88ad08972292f18dd70df08e9a277d48b1ee","target":"record","created_at":"2026-05-17T23:39:17Z","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":"d7f143abd25cf5e0badbb4bcd07a4c92f280dd932cf04950b144877a2f63e2aa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T21:19:19Z","title_canon_sha256":"0c278b0ac14636c2eda55a20dd71b589ec4e14087415265681e940a02ef0a9c6"},"schema_version":"1.0","source":{"id":"2506.16608","kind":"arxiv","version":3}},"canonical_sha256":"61db37cae1e4d48d01b7b6facca6ac566443dedd5de3ac8e96e390ce5ec3d537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61db37cae1e4d48d01b7b6facca6ac566443dedd5de3ac8e96e390ce5ec3d537","first_computed_at":"2026-05-17T23:39:17.909356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:17.909356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Igbs9gNPr7345ryLuOKn/aPQlAIZj/dj05BMxnqBsal+yDONYm5HnUrftmnYYJRP2V5JOFAHr4EjGCdujHVlDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:17.909840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16608","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22b3cfbf411838878ae760275f2e88ad08972292f18dd70df08e9a277d48b1ee","sha256:62412c24fd39835c6ca5fbf50642df47c2f52baf0bf3e9166a055d6012061f15"],"state_sha256":"e79c2e7fe47f75a3acf1045fc7bf64d5f48d70b1cbdc687638baa8c47dd25271"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GG4+CGqe7xTmueXOqVFnoKAOjsOl3hcFYKSSXkas8I79WYHSEE7kKKiYomcn3HKA/bZalIAgu5OGTDSzNgE+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T18:54:32.411941Z","bundle_sha256":"24e6c07caccdae9f1fed28a55b745091aefbe53101bd9d6949821cc6a6c20341"}}