{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RAAQVVY6HMPMPRUX22SNFEPPH3","short_pith_number":"pith:RAAQVVY6","canonical_record":{"source":{"id":"2411.19418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af67b8b9f1e16f054509e66007c2b55b84954e4062f0184ec413c45474171d4c","abstract_canon_sha256":"e90b2f7d5df78da63055ed46d1f774e379ebfa11f681825b040e1b6e4cdebf51"},"schema_version":"1.0"},"canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","source":{"kind":"arxiv","id":"2411.19418","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19418","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19418v2","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19418","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"RAAQVVY6HMPM","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"RAAQVVY6HMPMPRUX","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"RAAQVVY6","created_at":"2026-07-05T10:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RAAQVVY6HMPMPRUX22SNFEPPH3","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af67b8b9f1e16f054509e66007c2b55b84954e4062f0184ec413c45474171d4c","abstract_canon_sha256":"e90b2f7d5df78da63055ed46d1f774e379ebfa11f681825b040e1b6e4cdebf51"},"schema_version":"1.0"},"canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:28.568284Z","signature_b64":"SXtKTEPDbf4tShRBFNig6zOkbXo+rtsERs62wyUCiq0+SScT/iVZtOVOFx/n5rsgTXpAYaDRVUxiOymwQeZICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","last_reissued_at":"2026-07-05T10:28:28.567465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:28.567465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19418","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":"2026-07-05T10:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYSmPzq6qA/h0s5wxcvnmJuNoQNTCd7wZZnKYqloJRKhH37Gz7Luv390t5gGTciIIZI69IadZ6Gz8rC4x0i7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:49:50.965597Z"},"content_sha256":"e4b82a34a430292fbab08ba7b10f043ea15f3da5e6fcac274f6d21b573071b05","schema_version":"1.0","event_id":"sha256:e4b82a34a430292fbab08ba7b10f043ea15f3da5e6fcac274f6d21b573071b05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RAAQVVY6HMPMPRUX22SNFEPPH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Harshit Sikchi, Peter Stone, Siddhant Agarwal","submitted_at":"2024-11-29T00:09:39Z","abstract_excerpt":"Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as \"zero-shot learning\", this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present Proto Successor Measure: the basis set for all possible behaviors of a Reinforcement Learning Agent in a dynamical system. We prove that any poss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19418","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/2411.19418/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":"2026-07-05T10:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HMwONoYeYraHP09vI+2w6DyppD3YYQIuLVlZrVsg9I9TopmKJg6WsWgF5FjMkTYrZjv3QDEAdd81ByTZHpqFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:49:50.966208Z"},"content_sha256":"777f3d2a35cdc28a6b92b1bb4a439810f2974e9fb1bdcfd3f5530670ddd9a856","schema_version":"1.0","event_id":"sha256:777f3d2a35cdc28a6b92b1bb4a439810f2974e9fb1bdcfd3f5530670ddd9a856"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/bundle.json","state_url":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/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":"2026-08-08T02:49:50Z","links":{"resolver":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3","bundle":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/bundle.json","state":"https://pith.science/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RAAQVVY6HMPMPRUX22SNFEPPH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RAAQVVY6HMPMPRUX22SNFEPPH3","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":"e90b2f7d5df78da63055ed46d1f774e379ebfa11f681825b040e1b6e4cdebf51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","title_canon_sha256":"af67b8b9f1e16f054509e66007c2b55b84954e4062f0184ec413c45474171d4c"},"schema_version":"1.0","source":{"id":"2411.19418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19418","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19418v2","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19418","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"RAAQVVY6HMPM","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"RAAQVVY6HMPMPRUX","created_at":"2026-07-05T10:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"RAAQVVY6","created_at":"2026-07-05T10:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:777f3d2a35cdc28a6b92b1bb4a439810f2974e9fb1bdcfd3f5530670ddd9a856","target":"graph","created_at":"2026-07-05T10:28:28Z","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/2411.19418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as \"zero-shot learning\", this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present Proto Successor Measure: the basis set for all possible behaviors of a Reinforcement Learning Agent in a dynamical system. We prove that any poss","authors_text":"Amy Zhang, Harshit Sikchi, Peter Stone, Siddhant Agarwal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19418","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:e4b82a34a430292fbab08ba7b10f043ea15f3da5e6fcac274f6d21b573071b05","target":"record","created_at":"2026-07-05T10:28:28Z","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":"e90b2f7d5df78da63055ed46d1f774e379ebfa11f681825b040e1b6e4cdebf51","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T00:09:39Z","title_canon_sha256":"af67b8b9f1e16f054509e66007c2b55b84954e4062f0184ec413c45474171d4c"},"schema_version":"1.0","source":{"id":"2411.19418","kind":"arxiv","version":2}},"canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88010ad71e3b1ec7c697d6a4d291ef3ef4cc1dfab05c691159dfd059934c5d1a","first_computed_at":"2026-07-05T10:28:28.567465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:28.567465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SXtKTEPDbf4tShRBFNig6zOkbXo+rtsERs62wyUCiq0+SScT/iVZtOVOFx/n5rsgTXpAYaDRVUxiOymwQeZICw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:28.568284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4b82a34a430292fbab08ba7b10f043ea15f3da5e6fcac274f6d21b573071b05","sha256:777f3d2a35cdc28a6b92b1bb4a439810f2974e9fb1bdcfd3f5530670ddd9a856"],"state_sha256":"5fb5e3374dacfc0a728d642399eb93d4424141fd4c482d257a61cbf5df56e826"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hTjMCzX4t2WkcsscfElSE93gb2UguWYs+0bQCR1bOK0cIlPmODtP51RE66a7CMmL0vhv5bZD7e4yHs+Cx1MDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:49:50.971213Z","bundle_sha256":"bd650d87deed6433b303da0e0f0988071e30ccf31b808880df90bae14ef6e866"}}