{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AGIJK4UIMOMG43IQQBCVJJPGQT","short_pith_number":"pith:AGIJK4UI","canonical_record":{"source":{"id":"2607.21120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T09:55:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7ec0c78485c5c2ca7c59cc4ea72435a0f8920f95d7ed9bfd56192519acba577","abstract_canon_sha256":"3b9b6739683aa683fc9a4c62b5386d9e93509e0aee1aebd93f5eb83d5d73bae4"},"schema_version":"1.0"},"canonical_sha256":"019095728863986e6d10804554a5e684f6a8995c1d128157cd885c3d1b3a7e9c","source":{"kind":"arxiv","id":"2607.21120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21120","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21120v1","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21120","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"AGIJK4UIMOMG","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"AGIJK4UIMOMG43IQ","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"AGIJK4UI","created_at":"2026-07-24T01:23:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AGIJK4UIMOMG43IQQBCVJJPGQT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T09:55:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7ec0c78485c5c2ca7c59cc4ea72435a0f8920f95d7ed9bfd56192519acba577","abstract_canon_sha256":"3b9b6739683aa683fc9a4c62b5386d9e93509e0aee1aebd93f5eb83d5d73bae4"},"schema_version":"1.0"},"canonical_sha256":"019095728863986e6d10804554a5e684f6a8995c1d128157cd885c3d1b3a7e9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:53.797784Z","signature_b64":"eRvUuRn8D12TH8iFTMCiJVqDeiNShKjJ/IFH9nxV0oPEaYDJ1ZVtgKAidnHZqjptSlKsbV9z5B9LZDDrz4dBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"019095728863986e6d10804554a5e684f6a8995c1d128157cd885c3d1b3a7e9c","last_reissued_at":"2026-07-24T01:23:53.796915Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:53.796915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21120","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":"2026-07-24T01:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7k5TzfPeL75cDORzr+zLKBuyvu3pllNJac7gVisfPRD+CicoYR40sQ1FKgarrv3kRqgeOvGq23lQYjmnp78DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:55:37.021242Z"},"content_sha256":"bc24645f53380d7ab3b2ebec9ab855f8c0a75def6811931d01d7aa8ca1563a18","schema_version":"1.0","event_id":"sha256:bc24645f53380d7ab3b2ebec9ab855f8c0a75def6811931d01d7aa8ca1563a18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AGIJK4UIMOMG43IQQBCVJJPGQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relative Value Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling","submitted_at":"2026-07-23T09:55:45Z","abstract_excerpt":"In reinforcement learning, critics typically estimate absolute state values $V(s)$, estimating how good a particular situation is in isolation. However, it turns out that only differences in value are relevant for control. Motivated by this, we propose Relative Value Learning (RV), a framework that learns value differences directly via an antisymmetric function $\\Delta(s_i, s_j) = V(s_i) - V(s_j)$. We introduce a pairwise Bellman operator and prove it is a $\\gamma$-contraction with a unique fixed point equal to the true value differences, derive well-posed $1$-step, $n$-step and $\\lambda$-retu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21120","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/2607.21120/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":"2026-07-24T01:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIBhTPHecK5TWkiC5kx1w54/c1yo7zRjbpn5jnumoaBPPnouqc1VOxYJGYZ3FXqPoUxqEf985FkkDWeP3XS6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:55:37.021753Z"},"content_sha256":"bf549e1f57facb026ccbe0d605e7eb8371c5aa32aee5b9db870b6e4a0fede2d9","schema_version":"1.0","event_id":"sha256:bf549e1f57facb026ccbe0d605e7eb8371c5aa32aee5b9db870b6e4a0fede2d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/bundle.json","state_url":"https://pith.science/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/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":"2026-08-21T14:55:37Z","links":{"resolver":"https://pith.science/pith/AGIJK4UIMOMG43IQQBCVJJPGQT","bundle":"https://pith.science/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/bundle.json","state":"https://pith.science/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGIJK4UIMOMG43IQQBCVJJPGQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AGIJK4UIMOMG43IQQBCVJJPGQT","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":"3b9b6739683aa683fc9a4c62b5386d9e93509e0aee1aebd93f5eb83d5d73bae4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T09:55:45Z","title_canon_sha256":"c7ec0c78485c5c2ca7c59cc4ea72435a0f8920f95d7ed9bfd56192519acba577"},"schema_version":"1.0","source":{"id":"2607.21120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21120","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21120v1","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21120","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"AGIJK4UIMOMG","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"AGIJK4UIMOMG43IQ","created_at":"2026-07-24T01:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"AGIJK4UI","created_at":"2026-07-24T01:23:53Z"}],"graph_snapshots":[{"event_id":"sha256:bf549e1f57facb026ccbe0d605e7eb8371c5aa32aee5b9db870b6e4a0fede2d9","target":"graph","created_at":"2026-07-24T01:23:53Z","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/2607.21120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, critics typically estimate absolute state values $V(s)$, estimating how good a particular situation is in isolation. However, it turns out that only differences in value are relevant for control. Motivated by this, we propose Relative Value Learning (RV), a framework that learns value differences directly via an antisymmetric function $\\Delta(s_i, s_j) = V(s_i) - V(s_j)$. We introduce a pairwise Bellman operator and prove it is a $\\gamma$-contraction with a unique fixed point equal to the true value differences, derive well-posed $1$-step, $n$-step and $\\lambda$-retu","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T09:55:45Z","title":"Relative Value Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21120","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:bc24645f53380d7ab3b2ebec9ab855f8c0a75def6811931d01d7aa8ca1563a18","target":"record","created_at":"2026-07-24T01:23:53Z","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":"3b9b6739683aa683fc9a4c62b5386d9e93509e0aee1aebd93f5eb83d5d73bae4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T09:55:45Z","title_canon_sha256":"c7ec0c78485c5c2ca7c59cc4ea72435a0f8920f95d7ed9bfd56192519acba577"},"schema_version":"1.0","source":{"id":"2607.21120","kind":"arxiv","version":1}},"canonical_sha256":"019095728863986e6d10804554a5e684f6a8995c1d128157cd885c3d1b3a7e9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"019095728863986e6d10804554a5e684f6a8995c1d128157cd885c3d1b3a7e9c","first_computed_at":"2026-07-24T01:23:53.796915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:53.796915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eRvUuRn8D12TH8iFTMCiJVqDeiNShKjJ/IFH9nxV0oPEaYDJ1ZVtgKAidnHZqjptSlKsbV9z5B9LZDDrz4dBCw==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:53.797784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc24645f53380d7ab3b2ebec9ab855f8c0a75def6811931d01d7aa8ca1563a18","sha256:bf549e1f57facb026ccbe0d605e7eb8371c5aa32aee5b9db870b6e4a0fede2d9"],"state_sha256":"bf414daf69c3283c155803f8b2b87b612345e5256f51b29128d55bad480ee91d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kO4gSsanw4RtGTtcPZcbSQ/FnVvXohSaUzmn0oZVx9QkvLELcZf+qBDMzvM5ZIDY8y6zKh/WmEboihDgvuLFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:55:37.026875Z","bundle_sha256":"a6db00f21405dd28873f07762a0061841928efc21e0f99d9c91e9d175446ebb7"}}