{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YAVWVMMO4IVGXRUWAN3PDZ6RVX","short_pith_number":"pith:YAVWVMMO","canonical_record":{"source":{"id":"1901.05351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fa81fc7d9ae356e95ebd08fbd2daecc4d044643bba39bded841594d069556b5","abstract_canon_sha256":"dfebd4f4e824c510eb64097331696536e1c05797bb23951fd60fb439f2d4411a"},"schema_version":"1.0"},"canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","source":{"kind":"arxiv","id":"1901.05351","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.05351","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"1901.05351v2","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05351","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"YAVWVMMO4IVG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YAVWVMMO4IVGXRUW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YAVWVMMO","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YAVWVMMO4IVGXRUWAN3PDZ6RVX","target":"record","payload":{"canonical_record":{"source":{"id":"1901.05351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fa81fc7d9ae356e95ebd08fbd2daecc4d044643bba39bded841594d069556b5","abstract_canon_sha256":"dfebd4f4e824c510eb64097331696536e1c05797bb23951fd60fb439f2d4411a"},"schema_version":"1.0"},"canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:09.069410Z","signature_b64":"B4qCV08nTUD5dFAaYJG1h6RYA+FRKtPgbhXCmesNh+Cm+tOYTOROHPi4xvU18HyqkpIkTc5lQO8pxZQ12EiPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","last_reissued_at":"2026-05-17T23:56:09.068689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:09.068689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.05351","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":"2026-05-17T23:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tsLIr74u4kd3oIbGO4+W11hFS8eWaCTGtHkMg77nQpklxZkE5389Iu0IbX9KWI4avBNoDIcPV8NBEgudphaXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T13:04:03.157394Z"},"content_sha256":"80238ad8e5ee9f34f75ff898dcf263e549319d5cbadfee320e775b20e183a027","schema_version":"1.0","event_id":"sha256:80238ad8e5ee9f34f75ff898dcf263e549319d5cbadfee320e775b20e183a027"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YAVWVMMO4IVGXRUWAN3PDZ6RVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Learning on Graphs: A Reinforcement Learning Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Laura Toni, Sephora Madjiheurem","submitted_at":"2019-01-16T15:44:13Z","abstract_excerpt":"In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05351","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":""},"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":"2026-05-17T23:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ziUiXnO/8IctH6My7LhsVb9mqnqE7e4pW7a1ReYOOohv8/2AryEUixF4b4SxRegVEA/Ie7fUJEamUG1syCSEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T13:04:03.157735Z"},"content_sha256":"3de2af7d49f1bb893df6b78219e51152bbe38be326a7dbb7ca57c1bc1847ab10","schema_version":"1.0","event_id":"sha256:3de2af7d49f1bb893df6b78219e51152bbe38be326a7dbb7ca57c1bc1847ab10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/bundle.json","state_url":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/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":"2026-06-22T13:04:03Z","links":{"resolver":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX","bundle":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/bundle.json","state":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YAVWVMMO4IVGXRUWAN3PDZ6RVX","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":"dfebd4f4e824c510eb64097331696536e1c05797bb23951fd60fb439f2d4411a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","title_canon_sha256":"7fa81fc7d9ae356e95ebd08fbd2daecc4d044643bba39bded841594d069556b5"},"schema_version":"1.0","source":{"id":"1901.05351","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.05351","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"1901.05351v2","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05351","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"YAVWVMMO4IVG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YAVWVMMO4IVGXRUW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YAVWVMMO","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:3de2af7d49f1bb893df6b78219e51152bbe38be326a7dbb7ca57c1bc1847ab10","target":"graph","created_at":"2026-05-17T23:56:09Z","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"},"paper":{"abstract_excerpt":"In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically sh","authors_text":"Laura Toni, Sephora Madjiheurem","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","title":"Representation Learning on Graphs: A Reinforcement Learning Application"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05351","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":"sha256:80238ad8e5ee9f34f75ff898dcf263e549319d5cbadfee320e775b20e183a027","target":"record","created_at":"2026-05-17T23:56:09Z","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":"dfebd4f4e824c510eb64097331696536e1c05797bb23951fd60fb439f2d4411a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","title_canon_sha256":"7fa81fc7d9ae356e95ebd08fbd2daecc4d044643bba39bded841594d069556b5"},"schema_version":"1.0","source":{"id":"1901.05351","kind":"arxiv","version":2}},"canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","first_computed_at":"2026-05-17T23:56:09.068689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:09.068689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4qCV08nTUD5dFAaYJG1h6RYA+FRKtPgbhXCmesNh+Cm+tOYTOROHPi4xvU18HyqkpIkTc5lQO8pxZQ12EiPCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:09.069410Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.05351","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80238ad8e5ee9f34f75ff898dcf263e549319d5cbadfee320e775b20e183a027","sha256:3de2af7d49f1bb893df6b78219e51152bbe38be326a7dbb7ca57c1bc1847ab10"],"state_sha256":"0b9bd71c0dcb62d0a82fd9a58936a3b13b5e88dcaecf7b6743654bc60b263b94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHn5HaKfwzheRX57HMaWzziEMapyDyQVkW8oSPycHEf4Vl1l6m6+zpA5lT9MJhsF6iwBJhi9s2ZPgU4AEzV4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T13:04:03.159691Z","bundle_sha256":"5e4162b07a41754581fb1fd3bb5d16a5ed22cee9c854b20f180b9cebc6d53726"}}