{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7Z2LNPZS6GXPISXI57HRH6F2E6","short_pith_number":"pith:7Z2LNPZS","schema_version":"1.0","canonical_sha256":"fe74b6bf32f1aef44ae8efcf13f8ba27a52f2405328d9e413184d2f01f998a70","source":{"kind":"arxiv","id":"2504.16595","version":1},"attestation_state":"computed","paper":{"title":"HERB: Human-augmented Efficient Reinforcement learning for Bin-packing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Atabak Dehban, Egidio Falotico, Gojko Perovic, Gon\\c{c}alo Teixeira, Jos\\'e Santos-Victor, Nuno Ferreira Duarte","submitted_at":"2025-04-23T10:24:36Z","abstract_excerpt":"Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of "},"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":"2504.16595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-23T10:24:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0d54d023fe32e54bcdcda0a492470900f7bb5c3552fad66b6b9dcb1505ca0ea","abstract_canon_sha256":"960bc3bd3e6ecd27a256eff1eb82104dace20b90c82840c64c89a0d6afc4c69c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:01.971026Z","signature_b64":"Lx8ieniihfO4SIp1ruao79cc/0UmMCCqwR1sAfNTE4TYpzZGvH1k1PBXtTJG3sqHVw1qtMVNVfNlU3SpT7lmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe74b6bf32f1aef44ae8efcf13f8ba27a52f2405328d9e413184d2f01f998a70","last_reissued_at":"2026-07-05T10:53:01.970563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:01.970563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HERB: Human-augmented Efficient Reinforcement learning for Bin-packing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Atabak Dehban, Egidio Falotico, Gojko Perovic, Gon\\c{c}alo Teixeira, Jos\\'e Santos-Victor, Nuno Ferreira Duarte","submitted_at":"2025-04-23T10:24:36Z","abstract_excerpt":"Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16595","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/2504.16595/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":"2504.16595","created_at":"2026-07-05T10:53:01.970623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16595v1","created_at":"2026-07-05T10:53:01.970623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16595","created_at":"2026-07-05T10:53:01.970623+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z2LNPZS6GXP","created_at":"2026-07-05T10:53:01.970623+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z2LNPZS6GXPISXI","created_at":"2026-07-05T10:53:01.970623+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z2LNPZS","created_at":"2026-07-05T10:53:01.970623+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/7Z2LNPZS6GXPISXI57HRH6F2E6","json":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6.json","graph_json":"https://pith.science/api/pith-number/7Z2LNPZS6GXPISXI57HRH6F2E6/graph.json","events_json":"https://pith.science/api/pith-number/7Z2LNPZS6GXPISXI57HRH6F2E6/events.json","paper":"https://pith.science/paper/7Z2LNPZS"},"agent_actions":{"view_html":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6","download_json":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6.json","view_paper":"https://pith.science/paper/7Z2LNPZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16595&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z2LNPZS6GXPISXI57HRH6F2E6/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z2LNPZS6GXPISXI57HRH6F2E6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6/action/storage_attestation","attest_author":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6/action/author_attestation","sign_citation":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6/action/citation_signature","submit_replication":"https://pith.science/pith/7Z2LNPZS6GXPISXI57HRH6F2E6/action/replication_record"}},"created_at":"2026-07-05T10:53:01.970623+00:00","updated_at":"2026-07-05T10:53:01.970623+00:00"}