{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E6QGJUQZJ6WX2BALBJXC6CJA4D","short_pith_number":"pith:E6QGJUQZ","canonical_record":{"source":{"id":"2305.13030","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-22T13:33:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7faa3da7a5799490ee336f1fa8ada7342d290b83e8a774cfa148b6e612ad5a17","abstract_canon_sha256":"fec1f721d0b77f76d78af2960c202f812bb08533326174652cc830677ee458b2"},"schema_version":"1.0"},"canonical_sha256":"27a064d2194fad7d040b0a6e2f0920e0f1c8d414f1ef085864315ae5ad66490f","source":{"kind":"arxiv","id":"2305.13030","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13030","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13030v4","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13030","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"E6QGJUQZJ6WX","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"E6QGJUQZJ6WX2BAL","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"E6QGJUQZ","created_at":"2026-07-05T07:25:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E6QGJUQZJ6WX2BALBJXC6CJA4D","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13030","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-22T13:33:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7faa3da7a5799490ee336f1fa8ada7342d290b83e8a774cfa148b6e612ad5a17","abstract_canon_sha256":"fec1f721d0b77f76d78af2960c202f812bb08533326174652cc830677ee458b2"},"schema_version":"1.0"},"canonical_sha256":"27a064d2194fad7d040b0a6e2f0920e0f1c8d414f1ef085864315ae5ad66490f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:41.852611Z","signature_b64":"XOC1Wka3MTBDrCbo/jmzUlvyBHHtmAof0565875yyru5rud00Vof0bxM0KFHpOk6YoGDwMFThNkW9ujcgbzsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27a064d2194fad7d040b0a6e2f0920e0f1c8d414f1ef085864315ae5ad66490f","last_reissued_at":"2026-07-05T07:25:41.852177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:41.852177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13030","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqzfVIxoS66uHShTXna3BmVfBAxm7lrVoLawYdMGXa7iDQivCCew4nmAid7220LLBt6NS5dCxApU73x6A7aLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:17:11.873488Z"},"content_sha256":"8d3f7de00d05be6fd75bc344ea7f7de8c17eefbf025346fd9c9e692526f435ee","schema_version":"1.0","event_id":"sha256:8d3f7de00d05be6fd75bc344ea7f7de8c17eefbf025346fd9c9e692526f435ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E6QGJUQZJ6WX2BALBJXC6CJA4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Atom Scott, Hiroshi Nakahara, Kazushi Tsutsui, Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara","submitted_at":"2023-05-22T13:33:37Z","abstract_excerpt":"Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13030","kind":"arxiv","version":4},"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/2305.13030/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vFJghrdZp14dX9yzdeg8hcFCWH7DRKyyTFzHm6RPmchnFGJTc/j7+tCLvw6yJSWqSL4yyl9p2dyHbaaxAA9OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:17:11.874006Z"},"content_sha256":"683d0993bfd6240c60b867b9dbd9ee272d924528332060cb57fda7ec906c2113","schema_version":"1.0","event_id":"sha256:683d0993bfd6240c60b867b9dbd9ee272d924528332060cb57fda7ec906c2113"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/bundle.json","state_url":"https://pith.science/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T18:17:11Z","links":{"resolver":"https://pith.science/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D","bundle":"https://pith.science/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/bundle.json","state":"https://pith.science/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E6QGJUQZJ6WX2BALBJXC6CJA4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E6QGJUQZJ6WX2BALBJXC6CJA4D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fec1f721d0b77f76d78af2960c202f812bb08533326174652cc830677ee458b2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-22T13:33:37Z","title_canon_sha256":"7faa3da7a5799490ee336f1fa8ada7342d290b83e8a774cfa148b6e612ad5a17"},"schema_version":"1.0","source":{"id":"2305.13030","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13030","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13030v4","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13030","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"E6QGJUQZJ6WX","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"E6QGJUQZJ6WX2BAL","created_at":"2026-07-05T07:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"E6QGJUQZ","created_at":"2026-07-05T07:25:41Z"}],"graph_snapshots":[{"event_id":"sha256:683d0993bfd6240c60b867b9dbd9ee272d924528332060cb57fda7ec906c2113","target":"graph","created_at":"2026-07-05T07:25:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We a","authors_text":"Atom Scott, Hiroshi Nakahara, Kazushi Tsutsui, Keisuke Fujii, Naoya Takeishi, Yoshinobu Kawahara","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-22T13:33:37Z","title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13030","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8d3f7de00d05be6fd75bc344ea7f7de8c17eefbf025346fd9c9e692526f435ee","target":"record","created_at":"2026-07-05T07:25:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fec1f721d0b77f76d78af2960c202f812bb08533326174652cc830677ee458b2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-22T13:33:37Z","title_canon_sha256":"7faa3da7a5799490ee336f1fa8ada7342d290b83e8a774cfa148b6e612ad5a17"},"schema_version":"1.0","source":{"id":"2305.13030","kind":"arxiv","version":4}},"canonical_sha256":"27a064d2194fad7d040b0a6e2f0920e0f1c8d414f1ef085864315ae5ad66490f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27a064d2194fad7d040b0a6e2f0920e0f1c8d414f1ef085864315ae5ad66490f","first_computed_at":"2026-07-05T07:25:41.852177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:41.852177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XOC1Wka3MTBDrCbo/jmzUlvyBHHtmAof0565875yyru5rud00Vof0bxM0KFHpOk6YoGDwMFThNkW9ujcgbzsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:41.852611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13030","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d3f7de00d05be6fd75bc344ea7f7de8c17eefbf025346fd9c9e692526f435ee","sha256:683d0993bfd6240c60b867b9dbd9ee272d924528332060cb57fda7ec906c2113"],"state_sha256":"ed64b91e4c052a4f5a08e700ec10d08b08239bc2cf3b7b6cfcddccf44b5e10e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81X0M2pjDQGCrFBjybo8OvCwU0TD5agInK4mclVST8Gg457L+4vnNqIaPeZzqkEFKFbt2gZ953CTMf587BJ4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T18:17:11.879131Z","bundle_sha256":"9bc48c44d790d71d3cf88d2b811457833cb03e69bd852121ab4d853abafb1297"}}