{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2GWE2LN23T3JBOHDXAJMMRIK6A","short_pith_number":"pith:2GWE2LN2","canonical_record":{"source":{"id":"2605.31289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:24:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"20bb16083ab11b25c22ea791c3d7b6902607eff7f06222473930681e82fe381e","abstract_canon_sha256":"ec6cf38e2e3da52388c9b5c0b274991ca4ff6fbde4977deacd9dbe64e3c9ba66"},"schema_version":"1.0"},"canonical_sha256":"d1ac4d2dbadcf690b8e3b812c6450af0382b82d3acb5f265b4a9c7467554dbc0","source":{"kind":"arxiv","id":"2605.31289","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31289","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31289v1","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31289","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"2GWE2LN23T3J","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"2GWE2LN23T3JBOHD","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"2GWE2LN2","created_at":"2026-06-01T01:04:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2GWE2LN23T3JBOHDXAJMMRIK6A","target":"record","payload":{"canonical_record":{"source":{"id":"2605.31289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:24:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"20bb16083ab11b25c22ea791c3d7b6902607eff7f06222473930681e82fe381e","abstract_canon_sha256":"ec6cf38e2e3da52388c9b5c0b274991ca4ff6fbde4977deacd9dbe64e3c9ba66"},"schema_version":"1.0"},"canonical_sha256":"d1ac4d2dbadcf690b8e3b812c6450af0382b82d3acb5f265b4a9c7467554dbc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:09.175442Z","signature_b64":"79gTKfAObyj6QtOXr1+MT9q9eiLcvsar/eUlcbMFGZtJFEMy9ke2MkpWzY3tPKf3rGdOFG5GLO0euLbgenWwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1ac4d2dbadcf690b8e3b812c6450af0382b82d3acb5f265b4a9c7467554dbc0","last_reissued_at":"2026-06-01T01:04:09.174256Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:09.174256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.31289","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":"2026-06-01T01:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BfZvCR2qDSgzPVsMUQ15aSYsL42Qp1/soFKFAH2A7bdU0HZB35BfT1VKnXdezxvSFexHKq4FSVzAApJwyb4iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:36:03.355792Z"},"content_sha256":"924ef315b74313aae5056276c96c854b1edf83b80bc153b4c572c7077f001083","schema_version":"1.0","event_id":"sha256:924ef315b74313aae5056276c96c854b1edf83b80bc153b4c572c7077f001083"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2GWE2LN23T3JBOHDXAJMMRIK6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Terminal Representation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amir Esterhuysen, Anders Jonsson","submitted_at":"2026-05-29T13:24:28Z","abstract_excerpt":"Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are through the successor representation (SR) and the default representation (DR). The SR encodes states by the future trajectories they induce, capturing information flow decoupled from reward. The DR builds on this by weighting trajectories with reward, integrating credit-assignment structure into the representation. Eigenvectors of both representations have been used to support a range of downstream tasks -- including option discovery, reward shaping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31289","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/2605.31289/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":"2026-06-01T01:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BzAJxxdjZF3fT2byM6QVHezUSKSMnGmlZnNeIpkB8dvbwAD2WLKSZoyMI+1pvLmoJYVCBQxqBR0AUk07OL9dDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:36:03.356183Z"},"content_sha256":"d2c5ae783d66b83e4d548158d83ac86594473ba5c3abf8d36f2dbd1618c65894","schema_version":"1.0","event_id":"sha256:d2c5ae783d66b83e4d548158d83ac86594473ba5c3abf8d36f2dbd1618c65894"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/bundle.json","state_url":"https://pith.science/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/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":"2026-07-04T02:36:03Z","links":{"resolver":"https://pith.science/pith/2GWE2LN23T3JBOHDXAJMMRIK6A","bundle":"https://pith.science/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/bundle.json","state":"https://pith.science/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GWE2LN23T3JBOHDXAJMMRIK6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2GWE2LN23T3JBOHDXAJMMRIK6A","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":"ec6cf38e2e3da52388c9b5c0b274991ca4ff6fbde4977deacd9dbe64e3c9ba66","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:24:28Z","title_canon_sha256":"20bb16083ab11b25c22ea791c3d7b6902607eff7f06222473930681e82fe381e"},"schema_version":"1.0","source":{"id":"2605.31289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31289","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31289v1","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31289","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"2GWE2LN23T3J","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"2GWE2LN23T3JBOHD","created_at":"2026-06-01T01:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"2GWE2LN2","created_at":"2026-06-01T01:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:d2c5ae783d66b83e4d548158d83ac86594473ba5c3abf8d36f2dbd1618c65894","target":"graph","created_at":"2026-06-01T01:04:09Z","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/2605.31289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are through the successor representation (SR) and the default representation (DR). The SR encodes states by the future trajectories they induce, capturing information flow decoupled from reward. The DR builds on this by weighting trajectories with reward, integrating credit-assignment structure into the representation. Eigenvectors of both representations have been used to support a range of downstream tasks -- including option discovery, reward shaping","authors_text":"Amir Esterhuysen, Anders Jonsson","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:24:28Z","title":"The Terminal Representation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31289","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":"sha256:924ef315b74313aae5056276c96c854b1edf83b80bc153b4c572c7077f001083","target":"record","created_at":"2026-06-01T01:04:09Z","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":"ec6cf38e2e3da52388c9b5c0b274991ca4ff6fbde4977deacd9dbe64e3c9ba66","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T13:24:28Z","title_canon_sha256":"20bb16083ab11b25c22ea791c3d7b6902607eff7f06222473930681e82fe381e"},"schema_version":"1.0","source":{"id":"2605.31289","kind":"arxiv","version":1}},"canonical_sha256":"d1ac4d2dbadcf690b8e3b812c6450af0382b82d3acb5f265b4a9c7467554dbc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1ac4d2dbadcf690b8e3b812c6450af0382b82d3acb5f265b4a9c7467554dbc0","first_computed_at":"2026-06-01T01:04:09.174256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:09.174256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"79gTKfAObyj6QtOXr1+MT9q9eiLcvsar/eUlcbMFGZtJFEMy9ke2MkpWzY3tPKf3rGdOFG5GLO0euLbgenWwBQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:09.175442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:924ef315b74313aae5056276c96c854b1edf83b80bc153b4c572c7077f001083","sha256:d2c5ae783d66b83e4d548158d83ac86594473ba5c3abf8d36f2dbd1618c65894"],"state_sha256":"1a436fe4669838a23b41c10b4021c991fee47d7f3185340fc2a9eb52841bfc9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D37+QfQOz6nSqiwfNWEt1yQ5Me17CY9kJ73eG3gd/rEd3e0Ivlg0HZnFI6GMV2NL4rzitUUSffiuHtCiXqvpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T02:36:03.358134Z","bundle_sha256":"b29238766ddf4c2a73fb0f2dae2fff1e20ef8460466f46a7e1c57a09ea97bd57"}}