{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VN5Z7JIFCUY4TCWZCCQW2U5MMM","short_pith_number":"pith:VN5Z7JIF","canonical_record":{"source":{"id":"2410.19989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-25T22:11:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23f58ab1ccdf0babf71162c102504d00f7ad8bbb9ac14d22cd9ee67d444174ee","abstract_canon_sha256":"bde77434c053864139d8c93507016ca09f6e133132fef55a2cc8b86c505f0f5a"},"schema_version":"1.0"},"canonical_sha256":"ab7b9fa5051531c98ad910a16d53ac633251b026c030d00b6def2c3586932df2","source":{"kind":"arxiv","id":"2410.19989","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19989","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19989v2","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19989","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"VN5Z7JIFCUY4","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"VN5Z7JIFCUY4TCWZ","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"VN5Z7JIF","created_at":"2026-07-05T11:03:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VN5Z7JIFCUY4TCWZCCQW2U5MMM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-25T22:11:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23f58ab1ccdf0babf71162c102504d00f7ad8bbb9ac14d22cd9ee67d444174ee","abstract_canon_sha256":"bde77434c053864139d8c93507016ca09f6e133132fef55a2cc8b86c505f0f5a"},"schema_version":"1.0"},"canonical_sha256":"ab7b9fa5051531c98ad910a16d53ac633251b026c030d00b6def2c3586932df2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:17.844861Z","signature_b64":"xdu5PWkPhke1lijvKMpZXZrLWmRwC3AnQfqkoLVMlYfpOTts99YaO8SDsHlEAxyZUDF1SuN/oT5CQQJ5QMYpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7b9fa5051531c98ad910a16d53ac633251b026c030d00b6def2c3586932df2","last_reissued_at":"2026-07-05T11:03:17.844378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:17.844378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19989","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":"2026-07-05T11:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiG9y6sDKysLLwu5WElMGbYm48tAXsaPkcmGdbaBqlY7T4wU45HOOsT8hUwIjHhaADH7STizlZrmuVT9D086BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:17:01.852542Z"},"content_sha256":"2bdb8ea334cc63fb2ba2c933ea460a42d1d64789e2e2bfa997beace53dcdc5cf","schema_version":"1.0","event_id":"sha256:2bdb8ea334cc63fb2ba2c933ea460a42d1d64789e2e2bfa997beace53dcdc5cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VN5Z7JIFCUY4TCWZCCQW2U5MMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jan-Willem van de Meent, Karl Schmeckpeper, Lawson L. S. Wong, Lingfeng Sun, Ondrej Biza, Robert Platt, Tarik Kelestemur, Thomas Weng, Yecheng Jason Ma","submitted_at":"2024-10-25T22:11:54Z","abstract_excerpt":"Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning from a sparse reward signal. Designing dense reward functions is labour-intensive and requires domain expertise. In our work, we propose GCR (Goal-Contrastive Rewards), a dense reward function learning method that can be trained on passive video demonstrations. By using videos without actions, our method is easier to scale, as we can use arbitrary videos. GCR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19989","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.19989/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":"2026-07-05T11:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+rf16z/sV327b7vBCvJK9pkis0SIbXonrZnZnHjGCIXB0w9+zL1q1SbS37SImYr8eX6YEFf44Wtei+IS7PeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:17:01.853027Z"},"content_sha256":"b74f5d1daabb738f24922c148cc0c01a14a073d1ffdcaf4f7d6b5f1f3fda7d8a","schema_version":"1.0","event_id":"sha256:b74f5d1daabb738f24922c148cc0c01a14a073d1ffdcaf4f7d6b5f1f3fda7d8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/bundle.json","state_url":"https://pith.science/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/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":"2026-08-05T07:17:01Z","links":{"resolver":"https://pith.science/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM","bundle":"https://pith.science/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/bundle.json","state":"https://pith.science/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VN5Z7JIFCUY4TCWZCCQW2U5MMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VN5Z7JIFCUY4TCWZCCQW2U5MMM","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":"bde77434c053864139d8c93507016ca09f6e133132fef55a2cc8b86c505f0f5a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-25T22:11:54Z","title_canon_sha256":"23f58ab1ccdf0babf71162c102504d00f7ad8bbb9ac14d22cd9ee67d444174ee"},"schema_version":"1.0","source":{"id":"2410.19989","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19989","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19989v2","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19989","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"VN5Z7JIFCUY4","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"VN5Z7JIFCUY4TCWZ","created_at":"2026-07-05T11:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"VN5Z7JIF","created_at":"2026-07-05T11:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:b74f5d1daabb738f24922c148cc0c01a14a073d1ffdcaf4f7d6b5f1f3fda7d8a","target":"graph","created_at":"2026-07-05T11:03:17Z","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/2410.19989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning from a sparse reward signal. Designing dense reward functions is labour-intensive and requires domain expertise. In our work, we propose GCR (Goal-Contrastive Rewards), a dense reward function learning method that can be trained on passive video demonstrations. By using videos without actions, our method is easier to scale, as we can use arbitrary videos. GCR","authors_text":"Jan-Willem van de Meent, Karl Schmeckpeper, Lawson L. S. Wong, Lingfeng Sun, Ondrej Biza, Robert Platt, Tarik Kelestemur, Thomas Weng, Yecheng Jason Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-25T22:11:54Z","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19989","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":"sha256:2bdb8ea334cc63fb2ba2c933ea460a42d1d64789e2e2bfa997beace53dcdc5cf","target":"record","created_at":"2026-07-05T11:03:17Z","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":"bde77434c053864139d8c93507016ca09f6e133132fef55a2cc8b86c505f0f5a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-25T22:11:54Z","title_canon_sha256":"23f58ab1ccdf0babf71162c102504d00f7ad8bbb9ac14d22cd9ee67d444174ee"},"schema_version":"1.0","source":{"id":"2410.19989","kind":"arxiv","version":2}},"canonical_sha256":"ab7b9fa5051531c98ad910a16d53ac633251b026c030d00b6def2c3586932df2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab7b9fa5051531c98ad910a16d53ac633251b026c030d00b6def2c3586932df2","first_computed_at":"2026-07-05T11:03:17.844378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:17.844378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xdu5PWkPhke1lijvKMpZXZrLWmRwC3AnQfqkoLVMlYfpOTts99YaO8SDsHlEAxyZUDF1SuN/oT5CQQJ5QMYpBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:17.844861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19989","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bdb8ea334cc63fb2ba2c933ea460a42d1d64789e2e2bfa997beace53dcdc5cf","sha256:b74f5d1daabb738f24922c148cc0c01a14a073d1ffdcaf4f7d6b5f1f3fda7d8a"],"state_sha256":"de51a99f91e00fd765d4aa713f91bca105c4c336b6f56ce6a963782765d8f0bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yU+HCv+DwULFsd1Ej5WTyd/nYFP2U/Jx2r+tMOJvb7U45L1kew2GPN6IYAHx/QxgATnOPhYytlAvRAt7aS6aAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:17:01.856596Z","bundle_sha256":"cdfb3a0951b3fe2208312d9d9ba30540304976bd7dbe4c755a32d00b2d479a4d"}}