{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CTXOBTUXUHF35SQ2F534JDYH5C","short_pith_number":"pith:CTXOBTUX","canonical_record":{"source":{"id":"2606.21321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","cross_cats_sorted":[],"title_canon_sha256":"094b2f90f0ebcf685d2fa7a367990dabd36bb185820abcc05229f225e1b64dd9","abstract_canon_sha256":"c797e2aad7afbc8de89da784d2471b125c3950203bb2af6f635b1a76a025584f"},"schema_version":"1.0"},"canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","source":{"kind":"arxiv","id":"2606.21321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21321","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21321v1","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21321","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"CTXOBTUXUHF3","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"CTXOBTUXUHF35SQ2","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"CTXOBTUX","created_at":"2026-06-23T01:12:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CTXOBTUXUHF35SQ2F534JDYH5C","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","cross_cats_sorted":[],"title_canon_sha256":"094b2f90f0ebcf685d2fa7a367990dabd36bb185820abcc05229f225e1b64dd9","abstract_canon_sha256":"c797e2aad7afbc8de89da784d2471b125c3950203bb2af6f635b1a76a025584f"},"schema_version":"1.0"},"canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:37.150207Z","signature_b64":"jjDY6dDlhub/40Uh6zdhD3R57q+p9zyaalDYDa1acTVYmJ+M/+hpkPKGFN6vq5k25utw31BJy4edy9QPELXWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","last_reissued_at":"2026-06-23T01:12:37.149712Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:37.149712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21321","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":"2026-06-23T01:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9OBtY0Jgl//6LSsQTusO1WZeZCQtFdFnKPP5GqeUH/KStnRRdnehC+QrYLc4iLWuaW4PwxeVoevmvwYXo/+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:31:28.346909Z"},"content_sha256":"f0e83c8d8060190e52d4e5bbb45fe137fb28335d8aeb2d160b2ade1a655d948a","schema_version":"1.0","event_id":"sha256:f0e83c8d8060190e52d4e5bbb45fe137fb28335d8aeb2d160b2ade1a655d948a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CTXOBTUXUHF35SQ2F534JDYH5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Mone, Florian Felten, Frans A. Oliehoek, Luciano Cavalcante Siebert, Mark Fuge, Pradeep K. Murukannaiah, Zuzanna Osika","submitted_at":"2026-06-19T11:10:26Z","abstract_excerpt":"Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective via a scalarization function, which can be fragile: small changes in the weights can induce drastically different policies. Multi-objective reinforcement learning (MORL) instead produces sets of policies that explicitly represent trade-offs between objectives. However, these policies are typically presented to the decision maker only through their value vectors, which can obscure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21321","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/2606.21321/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":"2026-06-23T01:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZuDJRZPemaw8BW+04uwBZUr3u4cFGToUhUtPOKWJNv8Hoft50fgBq34SpGu4enCXScpiTSc2aErU6PrXdkQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:31:28.347353Z"},"content_sha256":"731e0c609dc58319e03175e50a578637de5babba18af336b2368e762cfd24d15","schema_version":"1.0","event_id":"sha256:731e0c609dc58319e03175e50a578637de5babba18af336b2368e762cfd24d15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/bundle.json","state_url":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTXOBTUXUHF35SQ2F534JDYH5C/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":"2026-06-28T11:31:28Z","links":{"resolver":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C","bundle":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/bundle.json","state":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTXOBTUXUHF35SQ2F534JDYH5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CTXOBTUXUHF35SQ2F534JDYH5C","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":"c797e2aad7afbc8de89da784d2471b125c3950203bb2af6f635b1a76a025584f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","title_canon_sha256":"094b2f90f0ebcf685d2fa7a367990dabd36bb185820abcc05229f225e1b64dd9"},"schema_version":"1.0","source":{"id":"2606.21321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21321","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21321v1","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21321","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"CTXOBTUXUHF3","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"CTXOBTUXUHF35SQ2","created_at":"2026-06-23T01:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"CTXOBTUX","created_at":"2026-06-23T01:12:37Z"}],"graph_snapshots":[{"event_id":"sha256:731e0c609dc58319e03175e50a578637de5babba18af336b2368e762cfd24d15","target":"graph","created_at":"2026-06-23T01:12:37Z","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/2606.21321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective via a scalarization function, which can be fragile: small changes in the weights can induce drastically different policies. Multi-objective reinforcement learning (MORL) instead produces sets of policies that explicitly represent trade-offs between objectives. However, these policies are typically presented to the decision maker only through their value vectors, which can obscure","authors_text":"Antonio Mone, Florian Felten, Frans A. Oliehoek, Luciano Cavalcante Siebert, Mark Fuge, Pradeep K. Murukannaiah, Zuzanna Osika","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21321","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:f0e83c8d8060190e52d4e5bbb45fe137fb28335d8aeb2d160b2ade1a655d948a","target":"record","created_at":"2026-06-23T01:12:37Z","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":"c797e2aad7afbc8de89da784d2471b125c3950203bb2af6f635b1a76a025584f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","title_canon_sha256":"094b2f90f0ebcf685d2fa7a367990dabd36bb185820abcc05229f225e1b64dd9"},"schema_version":"1.0","source":{"id":"2606.21321","kind":"arxiv","version":1}},"canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","first_computed_at":"2026-06-23T01:12:37.149712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:37.149712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jjDY6dDlhub/40Uh6zdhD3R57q+p9zyaalDYDa1acTVYmJ+M/+hpkPKGFN6vq5k25utw31BJy4edy9QPELXWCA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:37.150207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0e83c8d8060190e52d4e5bbb45fe137fb28335d8aeb2d160b2ade1a655d948a","sha256:731e0c609dc58319e03175e50a578637de5babba18af336b2368e762cfd24d15"],"state_sha256":"a9c46110434075285b0d997158c840d7078e20f2181ec88a87ede4d6b112e175"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4J8624+qicmNo4vUbxQh7pUgGHfj8xMgGTJeMWY+cdPYSlPkeRDMgory4gTQkn/M7Zrpx7fB4heczguumRYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:31:28.349585Z","bundle_sha256":"a1920198658c2f77f6d3a570fa3f88312bc545932fcd79812c38e45f1b7a1a46"}}