{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AZKDA4ZEK5EQEYBLTDEDLFOOEP","short_pith_number":"pith:AZKDA4ZE","canonical_record":{"source":{"id":"2506.09901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T16:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"3debd85b888b2c775d642e2e4320fea6971a2da4da652704b64c7c9c528cfca4","abstract_canon_sha256":"9b6126a0c49119573a232383a1c5495fc310f2743630139119f4a81a083df6ee"},"schema_version":"1.0"},"canonical_sha256":"0654307324574902602b98c83595ce23e91f5c0a9627a08353cf4951c6062b71","source":{"kind":"arxiv","id":"2506.09901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09901","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09901v1","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09901","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"AZKDA4ZEK5EQ","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"AZKDA4ZEK5EQEYBL","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"AZKDA4ZE","created_at":"2026-07-05T11:19:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AZKDA4ZEK5EQEYBLTDEDLFOOEP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.09901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T16:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"3debd85b888b2c775d642e2e4320fea6971a2da4da652704b64c7c9c528cfca4","abstract_canon_sha256":"9b6126a0c49119573a232383a1c5495fc310f2743630139119f4a81a083df6ee"},"schema_version":"1.0"},"canonical_sha256":"0654307324574902602b98c83595ce23e91f5c0a9627a08353cf4951c6062b71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:58.513206Z","signature_b64":"MUVgg9fx0E70hN0oKeffTEidvuWkUvUMYtyxHqnjW2sRyCkacpTjgxHa1jnHt0dLLF8Kryi8tana3SR290GjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0654307324574902602b98c83595ce23e91f5c0a9627a08353cf4951c6062b71","last_reissued_at":"2026-07-05T11:19:58.512746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:58.512746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.09901","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":"2026-07-05T11:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AgrKfqmg1gLDygAu5SPSEWUlV7cSAlV3zx7UIIogt0wnCJZCufz9rtMdMilBIjnNOJNxRbMpPWcJVKdnDARHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:08.253937Z"},"content_sha256":"a7fce9a0de1a107846e113499bffd12af2541ad0f2ffaa750e26c896e7602f9b","schema_version":"1.0","event_id":"sha256:a7fce9a0de1a107846e113499bffd12af2541ad0f2ffaa750e26c896e7602f9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AZKDA4ZEK5EQEYBLTDEDLFOOEP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"What are my options?\": Explaining RL Agents with Diverse Near-Optimal Alternatives (Extended)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cedric Langbort, Noel Brindise, Riya Shah, Vijeth Hebbar","submitted_at":"2025-06-11T16:15:56Z","abstract_excerpt":"In this work, we provide an extended discussion of a new approach to explainable Reinforcement Learning called Diverse Near-Optimal Alternatives (DNA), first proposed at L4DC 2025. DNA seeks a set of reasonable \"options\" for trajectory-planning agents, optimizing policies to produce qualitatively diverse trajectories in Euclidean space. In the spirit of explainability, these distinct policies are used to \"explain\" an agent's options in terms of available trajectory shapes from which a human user may choose. In particular, DNA applies to value function-based policies on Markov decision processe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09901","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/2506.09901/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":"2026-07-05T11:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KpJqdDVcAheWfq6CYvnzL/QKxK3FEqdR/OoWdfIolZcW8PBaMKrvIkdd+lSGr+B08QYQ8yobHC4tllJmm9E3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:56:08.254439Z"},"content_sha256":"80eb14bf32ebc5867023383a5ff3bd50a52fcb1cae90987762937628d6643131","schema_version":"1.0","event_id":"sha256:80eb14bf32ebc5867023383a5ff3bd50a52fcb1cae90987762937628d6643131"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/bundle.json","state_url":"https://pith.science/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/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":"2026-08-08T20:56:08Z","links":{"resolver":"https://pith.science/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP","bundle":"https://pith.science/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/bundle.json","state":"https://pith.science/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZKDA4ZEK5EQEYBLTDEDLFOOEP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AZKDA4ZEK5EQEYBLTDEDLFOOEP","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":"9b6126a0c49119573a232383a1c5495fc310f2743630139119f4a81a083df6ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T16:15:56Z","title_canon_sha256":"3debd85b888b2c775d642e2e4320fea6971a2da4da652704b64c7c9c528cfca4"},"schema_version":"1.0","source":{"id":"2506.09901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09901","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09901v1","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09901","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"AZKDA4ZEK5EQ","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"AZKDA4ZEK5EQEYBL","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"AZKDA4ZE","created_at":"2026-07-05T11:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:80eb14bf32ebc5867023383a5ff3bd50a52fcb1cae90987762937628d6643131","target":"graph","created_at":"2026-07-05T11:19:58Z","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/2506.09901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we provide an extended discussion of a new approach to explainable Reinforcement Learning called Diverse Near-Optimal Alternatives (DNA), first proposed at L4DC 2025. DNA seeks a set of reasonable \"options\" for trajectory-planning agents, optimizing policies to produce qualitatively diverse trajectories in Euclidean space. In the spirit of explainability, these distinct policies are used to \"explain\" an agent's options in terms of available trajectory shapes from which a human user may choose. In particular, DNA applies to value function-based policies on Markov decision processe","authors_text":"Cedric Langbort, Noel Brindise, Riya Shah, Vijeth Hebbar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T16:15:56Z","title":"\"What are my options?\": Explaining RL Agents with Diverse Near-Optimal Alternatives (Extended)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09901","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:a7fce9a0de1a107846e113499bffd12af2541ad0f2ffaa750e26c896e7602f9b","target":"record","created_at":"2026-07-05T11:19:58Z","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":"9b6126a0c49119573a232383a1c5495fc310f2743630139119f4a81a083df6ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T16:15:56Z","title_canon_sha256":"3debd85b888b2c775d642e2e4320fea6971a2da4da652704b64c7c9c528cfca4"},"schema_version":"1.0","source":{"id":"2506.09901","kind":"arxiv","version":1}},"canonical_sha256":"0654307324574902602b98c83595ce23e91f5c0a9627a08353cf4951c6062b71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0654307324574902602b98c83595ce23e91f5c0a9627a08353cf4951c6062b71","first_computed_at":"2026-07-05T11:19:58.512746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:58.512746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MUVgg9fx0E70hN0oKeffTEidvuWkUvUMYtyxHqnjW2sRyCkacpTjgxHa1jnHt0dLLF8Kryi8tana3SR290GjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:58.513206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7fce9a0de1a107846e113499bffd12af2541ad0f2ffaa750e26c896e7602f9b","sha256:80eb14bf32ebc5867023383a5ff3bd50a52fcb1cae90987762937628d6643131"],"state_sha256":"80a5f426abb8ff03e5c9b7d4707cfcca055a2d51ffa065f836ba4a8dd7a5e918"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9oooweTbqMTVNXxV0OkHl9zPqIhsvztAB0H2z/uQ2pF7bhdnN1uAlnvjVRIBjtVAo8CUCvxXSvzD5QrtrStBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:56:08.259366Z","bundle_sha256":"d24668643aa6c56b930952c417964513a5a15c44d5a2c9a386ab4ec5cce55939"}}