{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ORFRSRHOXYHVD4DJZ3DMEQT7L","short_pith_number":"pith:7ORFRSRH","schema_version":"1.0","canonical_sha256":"fba258ca2775f07a8f834e76361213fac3eedfc85f8a1d707a131d85d8e9abec","source":{"kind":"arxiv","id":"2412.07617","version":1},"attestation_state":"computed","paper":{"title":"Swarm Behavior Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Claudia Linnhoff-Popien, Jonas N\\\"u{\\ss}lein, Maximilian Zorn, Philipp Altmann","submitted_at":"2024-12-10T15:54:57Z","abstract_excerpt":"In sequential decision-making environments, the primary approaches for training agents are Reinforcement Learning (RL) and Imitation Learning (IL). Unlike RL, which relies on modeling a reward function, IL leverages expert demonstrations, where an expert policy $\\pi_e$ (e.g., a human) provides the desired behavior. Formally, a dataset $D$ of state-action pairs is provided: $D = {(s, a = \\pi_e(s))}$. A common technique within IL is Behavior Cloning (BC), where a policy $\\pi(s) = a$ is learned through supervised learning on $D$. Further improvements can be achieved by using an ensemble of $N$ in"},"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":"2412.07617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-10T15:54:57Z","cross_cats_sorted":[],"title_canon_sha256":"e6445dfb66c26f4a1ad51184271da384cca1e6193405b403069937dd07a4e60d","abstract_canon_sha256":"52469fbd233916a647d57d864f5f147c3614e69246e6ac5ada61c647856c9172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:12.454520Z","signature_b64":"D6h5f6YKsNdjVNnw+Tkeh4+FKdPAD/Aj/NjFZbJ7k4m4S1XbMxA+SuOwTkAVbAmjmU1yKRSF5DxuSmXrkWnSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba258ca2775f07a8f834e76361213fac3eedfc85f8a1d707a131d85d8e9abec","last_reissued_at":"2026-07-05T09:47:12.453949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:12.453949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swarm Behavior Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Claudia Linnhoff-Popien, Jonas N\\\"u{\\ss}lein, Maximilian Zorn, Philipp Altmann","submitted_at":"2024-12-10T15:54:57Z","abstract_excerpt":"In sequential decision-making environments, the primary approaches for training agents are Reinforcement Learning (RL) and Imitation Learning (IL). Unlike RL, which relies on modeling a reward function, IL leverages expert demonstrations, where an expert policy $\\pi_e$ (e.g., a human) provides the desired behavior. Formally, a dataset $D$ of state-action pairs is provided: $D = {(s, a = \\pi_e(s))}$. A common technique within IL is Behavior Cloning (BC), where a policy $\\pi(s) = a$ is learned through supervised learning on $D$. Further improvements can be achieved by using an ensemble of $N$ in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07617","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/2412.07617/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":"2412.07617","created_at":"2026-07-05T09:47:12.454014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07617v1","created_at":"2026-07-05T09:47:12.454014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07617","created_at":"2026-07-05T09:47:12.454014+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ORFRSRHOXYH","created_at":"2026-07-05T09:47:12.454014+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ORFRSRHOXYHVD4D","created_at":"2026-07-05T09:47:12.454014+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ORFRSRH","created_at":"2026-07-05T09:47:12.454014+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/7ORFRSRHOXYHVD4DJZ3DMEQT7L","json":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L.json","graph_json":"https://pith.science/api/pith-number/7ORFRSRHOXYHVD4DJZ3DMEQT7L/graph.json","events_json":"https://pith.science/api/pith-number/7ORFRSRHOXYHVD4DJZ3DMEQT7L/events.json","paper":"https://pith.science/paper/7ORFRSRH"},"agent_actions":{"view_html":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L","download_json":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L.json","view_paper":"https://pith.science/paper/7ORFRSRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07617&json=true","fetch_graph":"https://pith.science/api/pith-number/7ORFRSRHOXYHVD4DJZ3DMEQT7L/graph.json","fetch_events":"https://pith.science/api/pith-number/7ORFRSRHOXYHVD4DJZ3DMEQT7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L/action/storage_attestation","attest_author":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L/action/author_attestation","sign_citation":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L/action/citation_signature","submit_replication":"https://pith.science/pith/7ORFRSRHOXYHVD4DJZ3DMEQT7L/action/replication_record"}},"created_at":"2026-07-05T09:47:12.454014+00:00","updated_at":"2026-07-05T09:47:12.454014+00:00"}