{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EWGPDOUIKBXXS4YTRAFMVO5RD5","short_pith_number":"pith:EWGPDOUI","schema_version":"1.0","canonical_sha256":"258cf1ba88506f797313880acabbb11f439838dd023653074755480dc6702a1c","source":{"kind":"arxiv","id":"2501.04426","version":1},"attestation_state":"computed","paper":{"title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Georg Martius, Marin Vlastelica, Pavel Kolev","submitted_at":"2025-01-08T11:20:48Z","abstract_excerpt":"While many algorithms for diversity maximization under imitation constraints are online in nature, many applications require offline algorithms without environment interactions. Tackling this problem in the offline setting, however, presents significant challenges that require non-trivial, multi-stage optimization processes with non-stationary rewards. In this work, we present a novel offline algorithm that enhances diversity using an objective based on Van der Waals (VdW) force and successor features, and eliminates the need to learn a previously used skill discriminator. Moreover, by conditi"},"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":"2501.04426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T11:20:48Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"f0cb206cbf7d455abf0579f8563227473cfe2b45129b45bb2c2befd79c0f0dc9","abstract_canon_sha256":"bd57802676f033388c09a00bfed404e90229d8550a4182e4ea205f94feccb9c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:34.890386Z","signature_b64":"Mw8pMbN4+CAUs4zxxFVJPmkA/gGv7nXOxecHCXjYB1thUkEnLL/+6V/vX/cd65nWQrrO0WhcLbuu8Pg/26AVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258cf1ba88506f797313880acabbb11f439838dd023653074755480dc6702a1c","last_reissued_at":"2026-07-05T09:58:34.889942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:34.889942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Georg Martius, Marin Vlastelica, Pavel Kolev","submitted_at":"2025-01-08T11:20:48Z","abstract_excerpt":"While many algorithms for diversity maximization under imitation constraints are online in nature, many applications require offline algorithms without environment interactions. Tackling this problem in the offline setting, however, presents significant challenges that require non-trivial, multi-stage optimization processes with non-stationary rewards. In this work, we present a novel offline algorithm that enhances diversity using an objective based on Van der Waals (VdW) force and successor features, and eliminates the need to learn a previously used skill discriminator. Moreover, by conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04426","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/2501.04426/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":"2501.04426","created_at":"2026-07-05T09:58:34.889997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04426v1","created_at":"2026-07-05T09:58:34.889997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04426","created_at":"2026-07-05T09:58:34.889997+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWGPDOUIKBXX","created_at":"2026-07-05T09:58:34.889997+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWGPDOUIKBXXS4YT","created_at":"2026-07-05T09:58:34.889997+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWGPDOUI","created_at":"2026-07-05T09:58:34.889997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01432","citing_title":"The Geometry of Nonlinear Reinforcement Learning","ref_index":1994,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5","json":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5.json","graph_json":"https://pith.science/api/pith-number/EWGPDOUIKBXXS4YTRAFMVO5RD5/graph.json","events_json":"https://pith.science/api/pith-number/EWGPDOUIKBXXS4YTRAFMVO5RD5/events.json","paper":"https://pith.science/paper/EWGPDOUI"},"agent_actions":{"view_html":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5","download_json":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5.json","view_paper":"https://pith.science/paper/EWGPDOUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04426&json=true","fetch_graph":"https://pith.science/api/pith-number/EWGPDOUIKBXXS4YTRAFMVO5RD5/graph.json","fetch_events":"https://pith.science/api/pith-number/EWGPDOUIKBXXS4YTRAFMVO5RD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5/action/storage_attestation","attest_author":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5/action/author_attestation","sign_citation":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5/action/citation_signature","submit_replication":"https://pith.science/pith/EWGPDOUIKBXXS4YTRAFMVO5RD5/action/replication_record"}},"created_at":"2026-07-05T09:58:34.889997+00:00","updated_at":"2026-07-05T09:58:34.889997+00:00"}