{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:37O4FG423GJQIQGEEXSLBIDIV7","short_pith_number":"pith:37O4FG42","schema_version":"1.0","canonical_sha256":"dfddc29b9ad9930440c425e4b0a068afd687bde03b437fca54e2f9308e9d046e","source":{"kind":"arxiv","id":"2608.03753","version":1},"attestation_state":"computed","paper":{"title":"GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Protopapa, Davide Buoso, Francesca Pistilli, Georgia Chalvatzaki, Giuseppe Averta","submitted_at":"2026-08-04T14:43:41Z","abstract_excerpt":"Learning long-horizon manipulation skills with reinforcement learning remains challenging due to the complexity of reward design, the limited guidance of sparse rewards, and the high cost of manual subtask annotation. Visual demonstrations can provide supervision for reward learning, but rewards learned from raw pixels can be brittle and sensitive to visual variation, background appearance, and robot motion. In this work, we propose GORDON, a graph-based object-centric reward learning framework that learns dense rewards from action-free video demonstrations. Each visual scene is represented as"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-04T14:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"89024c43ed225fdb9cc49f02437f422fe333a84927044fbc9751314dd9a984d2","abstract_canon_sha256":"798da41152b103627b5ed34a479424361b21debdd4682c35d51b9cd08146bf5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:01.880354Z","signature_b64":"6O1wSa3fbQ+YgAjDkzIltd5qFwaa9VQW5xuZRRXGaMmPqk0xzITKY00y9JulAmdwi0UqtU9wu3PArFqvS6MDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfddc29b9ad9930440c425e4b0a068afd687bde03b437fca54e2f9308e9d046e","last_reissued_at":"2026-08-05T01:37:01.878770Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:01.878770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrea Protopapa, Davide Buoso, Francesca Pistilli, Georgia Chalvatzaki, Giuseppe Averta","submitted_at":"2026-08-04T14:43:41Z","abstract_excerpt":"Learning long-horizon manipulation skills with reinforcement learning remains challenging due to the complexity of reward design, the limited guidance of sparse rewards, and the high cost of manual subtask annotation. Visual demonstrations can provide supervision for reward learning, but rewards learned from raw pixels can be brittle and sensitive to visual variation, background appearance, and robot motion. In this work, we propose GORDON, a graph-based object-centric reward learning framework that learns dense rewards from action-free video demonstrations. Each visual scene is represented as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03753","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/2608.03753/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03753","created_at":"2026-08-05T01:37:01.879288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03753v1","created_at":"2026-08-05T01:37:01.879288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03753","created_at":"2026-08-05T01:37:01.879288+00:00"},{"alias_kind":"pith_short_12","alias_value":"37O4FG423GJQ","created_at":"2026-08-05T01:37:01.879288+00:00"},{"alias_kind":"pith_short_16","alias_value":"37O4FG423GJQIQGE","created_at":"2026-08-05T01:37:01.879288+00:00"},{"alias_kind":"pith_short_8","alias_value":"37O4FG42","created_at":"2026-08-05T01:37:01.879288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7","json":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7.json","graph_json":"https://pith.science/api/pith-number/37O4FG423GJQIQGEEXSLBIDIV7/graph.json","events_json":"https://pith.science/api/pith-number/37O4FG423GJQIQGEEXSLBIDIV7/events.json","paper":"https://pith.science/paper/37O4FG42"},"agent_actions":{"view_html":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7","download_json":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7.json","view_paper":"https://pith.science/paper/37O4FG42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03753&json=true","fetch_graph":"https://pith.science/api/pith-number/37O4FG423GJQIQGEEXSLBIDIV7/graph.json","fetch_events":"https://pith.science/api/pith-number/37O4FG423GJQIQGEEXSLBIDIV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7/action/storage_attestation","attest_author":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7/action/author_attestation","sign_citation":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7/action/citation_signature","submit_replication":"https://pith.science/pith/37O4FG423GJQIQGEEXSLBIDIV7/action/replication_record"}},"created_at":"2026-08-05T01:37:01.879288+00:00","updated_at":"2026-08-05T01:37:01.879288+00:00"}