{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUV3W3OTC7LO5RU55FIT6JB7OZ","short_pith_number":"pith:WUV3W3OT","schema_version":"1.0","canonical_sha256":"b52bbb6dd317d6eec69de9513f243f764e560bd9ff04696180c9c17bf8bf9501","source":{"kind":"arxiv","id":"2501.14856","version":2},"attestation_state":"computed","paper":{"title":"Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Anish Abhijit Diwan, Jan Peters, Jens Kober, Julen Urain","submitted_at":"2025-01-24T17:15:49Z","abstract_excerpt":"This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via re"},"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":"2501.14856","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-01-24T17:15:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d884d6d37f557f4592ce61202bda2491970f409d0d07b3ed117bae9ebbeec564","abstract_canon_sha256":"e236324db984af0dbd35720e08bde9ff6a50f93595ca0475390d7c73afa6c501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:07.634240Z","signature_b64":"xMmVMp8lCqkV+eLpanGcUIYfENm9jaePdj5EbJF8MzGHoeh3L0z+TyBQMK43Id7CSgTVw8r9K3PgkxCXeeuIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b52bbb6dd317d6eec69de9513f243f764e560bd9ff04696180c9c17bf8bf9501","last_reissued_at":"2026-07-05T10:13:07.633817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:07.633817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Anish Abhijit Diwan, Jan Peters, Jens Kober, Julen Urain","submitted_at":"2025-01-24T17:15:49Z","abstract_excerpt":"This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14856","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/2501.14856/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":"2501.14856","created_at":"2026-07-05T10:13:07.633874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14856v2","created_at":"2026-07-05T10:13:07.633874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14856","created_at":"2026-07-05T10:13:07.633874+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUV3W3OTC7LO","created_at":"2026-07-05T10:13:07.633874+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUV3W3OTC7LO5RU5","created_at":"2026-07-05T10:13:07.633874+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUV3W3OT","created_at":"2026-07-05T10:13:07.633874+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/WUV3W3OTC7LO5RU55FIT6JB7OZ","json":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ.json","graph_json":"https://pith.science/api/pith-number/WUV3W3OTC7LO5RU55FIT6JB7OZ/graph.json","events_json":"https://pith.science/api/pith-number/WUV3W3OTC7LO5RU55FIT6JB7OZ/events.json","paper":"https://pith.science/paper/WUV3W3OT"},"agent_actions":{"view_html":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ","download_json":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ.json","view_paper":"https://pith.science/paper/WUV3W3OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14856&json=true","fetch_graph":"https://pith.science/api/pith-number/WUV3W3OTC7LO5RU55FIT6JB7OZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WUV3W3OTC7LO5RU55FIT6JB7OZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ/action/storage_attestation","attest_author":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ/action/author_attestation","sign_citation":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ/action/citation_signature","submit_replication":"https://pith.science/pith/WUV3W3OTC7LO5RU55FIT6JB7OZ/action/replication_record"}},"created_at":"2026-07-05T10:13:07.633874+00:00","updated_at":"2026-07-05T10:13:07.633874+00:00"}