{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O6OIB7BKUWUDQT36773NSYBPFT","short_pith_number":"pith:O6OIB7BK","canonical_record":{"source":{"id":"2605.22123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T07:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"e556bdd4878d3ade891c6ba4ef307702ac520a530c87b49efcc8315469efc30a","abstract_canon_sha256":"cf00f6a881e6023573b1682a2a2271a11440afd9eac8f221b735cf5dd2915452"},"schema_version":"1.0"},"canonical_sha256":"779c80fc2aa5a8384f7efff6d9602f2cfef324e5729bc55fd813890c25a44a08","source":{"kind":"arxiv","id":"2605.22123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22123","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22123v1","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22123","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"O6OIB7BKUWUD","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"O6OIB7BKUWUDQT36","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"O6OIB7BK","created_at":"2026-05-22T01:04:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O6OIB7BKUWUDQT36773NSYBPFT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T07:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"e556bdd4878d3ade891c6ba4ef307702ac520a530c87b49efcc8315469efc30a","abstract_canon_sha256":"cf00f6a881e6023573b1682a2a2271a11440afd9eac8f221b735cf5dd2915452"},"schema_version":"1.0"},"canonical_sha256":"779c80fc2aa5a8384f7efff6d9602f2cfef324e5729bc55fd813890c25a44a08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:27.038746Z","signature_b64":"QWtI3R6bapFdiGV2KHIClU8OSPtT+ClJBOvE8LKROvCHqU/8W/lvpb0GUrhK1mMc32tskz1n5awbboxCScFWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"779c80fc2aa5a8384f7efff6d9602f2cfef324e5729bc55fd813890c25a44a08","last_reissued_at":"2026-05-22T01:04:27.038059Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:27.038059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22123","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":"2026-05-22T01:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03tGWtUgnZM3H7SK8XEhjUP5neHvuGXI+g7QLW170c05d/KaTNjHrv5wwPcEeLBQpp4tzuxryeQWrpgxybqXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:02:30.646516Z"},"content_sha256":"12ebb073ff4b0811f793bf800c4d32bd882e81072fb5bd105f97ea8770861856","schema_version":"1.0","event_id":"sha256:12ebb073ff4b0811f793bf800c4d32bd882e81072fb5bd105f97ea8770861856"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O6OIB7BKUWUDQT36773NSYBPFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chen yizhou, Guanqi Chen, Hua Chen, Jia Pan, Tengye Xu, Yangting Sun, Zhen Fu, Ziju Shen","submitted_at":"2026-05-21T07:55:35Z","abstract_excerpt":"Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants through different object instances, positions, and camera viewpoints. Recent vision-based reward models tend to memorize specific pixel distributions and fail to generalize beyond their training conditions. To address this, we propose a framework that learns invariant symbolic reward functions from as few as five demonstrations. The insight is to shift from visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22123","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/2605.22123/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":"2026-05-22T01:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhDff2BnmRUazxas8MeorfzCPNaid1sV/G5OHEwJaCPNyeH4CnSV2gJ0l0XybK+l4xGzqU6D5XHepj7Ntd2eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:02:30.647310Z"},"content_sha256":"e8101ddf334d2c435adcadb02e358d2eb6e3ad9f4ca817a2d20e6ae5f499a28e","schema_version":"1.0","event_id":"sha256:e8101ddf334d2c435adcadb02e358d2eb6e3ad9f4ca817a2d20e6ae5f499a28e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6OIB7BKUWUDQT36773NSYBPFT/bundle.json","state_url":"https://pith.science/pith/O6OIB7BKUWUDQT36773NSYBPFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6OIB7BKUWUDQT36773NSYBPFT/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":"2026-05-25T04:02:30Z","links":{"resolver":"https://pith.science/pith/O6OIB7BKUWUDQT36773NSYBPFT","bundle":"https://pith.science/pith/O6OIB7BKUWUDQT36773NSYBPFT/bundle.json","state":"https://pith.science/pith/O6OIB7BKUWUDQT36773NSYBPFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6OIB7BKUWUDQT36773NSYBPFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O6OIB7BKUWUDQT36773NSYBPFT","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":"cf00f6a881e6023573b1682a2a2271a11440afd9eac8f221b735cf5dd2915452","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T07:55:35Z","title_canon_sha256":"e556bdd4878d3ade891c6ba4ef307702ac520a530c87b49efcc8315469efc30a"},"schema_version":"1.0","source":{"id":"2605.22123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22123","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22123v1","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22123","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"O6OIB7BKUWUD","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"O6OIB7BKUWUDQT36","created_at":"2026-05-22T01:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"O6OIB7BK","created_at":"2026-05-22T01:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:e8101ddf334d2c435adcadb02e358d2eb6e3ad9f4ca817a2d20e6ae5f499a28e","target":"graph","created_at":"2026-05-22T01:04:27Z","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/2605.22123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants through different object instances, positions, and camera viewpoints. Recent vision-based reward models tend to memorize specific pixel distributions and fail to generalize beyond their training conditions. To address this, we propose a framework that learns invariant symbolic reward functions from as few as five demonstrations. The insight is to shift from visu","authors_text":"Chen yizhou, Guanqi Chen, Hua Chen, Jia Pan, Tengye Xu, Yangting Sun, Zhen Fu, Ziju Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T07:55:35Z","title":"Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22123","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":"sha256:12ebb073ff4b0811f793bf800c4d32bd882e81072fb5bd105f97ea8770861856","target":"record","created_at":"2026-05-22T01:04:27Z","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":"cf00f6a881e6023573b1682a2a2271a11440afd9eac8f221b735cf5dd2915452","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T07:55:35Z","title_canon_sha256":"e556bdd4878d3ade891c6ba4ef307702ac520a530c87b49efcc8315469efc30a"},"schema_version":"1.0","source":{"id":"2605.22123","kind":"arxiv","version":1}},"canonical_sha256":"779c80fc2aa5a8384f7efff6d9602f2cfef324e5729bc55fd813890c25a44a08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"779c80fc2aa5a8384f7efff6d9602f2cfef324e5729bc55fd813890c25a44a08","first_computed_at":"2026-05-22T01:04:27.038059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:27.038059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QWtI3R6bapFdiGV2KHIClU8OSPtT+ClJBOvE8LKROvCHqU/8W/lvpb0GUrhK1mMc32tskz1n5awbboxCScFWCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:27.038746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12ebb073ff4b0811f793bf800c4d32bd882e81072fb5bd105f97ea8770861856","sha256:e8101ddf334d2c435adcadb02e358d2eb6e3ad9f4ca817a2d20e6ae5f499a28e"],"state_sha256":"b93b067b9b0ac5ff49cf61020be2d0f578f3f9a86a8cc3b7ffa315130b230db9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obF6MG47xd6dvO0YbVxS3CQl7IPKeX47N0yxQwZJfDwLHaaUlbTaUOxpg0Mbx50Ek+q35XaR87NdypG/Q4HfCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T04:02:30.651618Z","bundle_sha256":"840355fea17b414eb1a9872818703daa72dba912ea1b3c570280d7110e2b559c"}}