{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VC4Q56DGGYYTAADGPP2TODBMJV","short_pith_number":"pith:VC4Q56DG","canonical_record":{"source":{"id":"2110.08176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T16:03:57Z","cross_cats_sorted":["cs.HC","cs.MA"],"title_canon_sha256":"96365b622bc69f9539d0cca4fcda030a9497d1f61e6b8eda78036a7904c37cac","abstract_canon_sha256":"fcceef5e5ebea3cd27d9de266168fa25c43d44ed601c1ff631c923ef6d72a31b"},"schema_version":"1.0"},"canonical_sha256":"a8b90ef86636313000667bf5370c2c4d7804cbae3b33795258a42a1f49a23396","source":{"kind":"arxiv","id":"2110.08176","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08176","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08176v2","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08176","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"VC4Q56DGGYYT","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"VC4Q56DGGYYTAADG","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"VC4Q56DG","created_at":"2026-07-05T03:46:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VC4Q56DGGYYTAADGPP2TODBMJV","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T16:03:57Z","cross_cats_sorted":["cs.HC","cs.MA"],"title_canon_sha256":"96365b622bc69f9539d0cca4fcda030a9497d1f61e6b8eda78036a7904c37cac","abstract_canon_sha256":"fcceef5e5ebea3cd27d9de266168fa25c43d44ed601c1ff631c923ef6d72a31b"},"schema_version":"1.0"},"canonical_sha256":"a8b90ef86636313000667bf5370c2c4d7804cbae3b33795258a42a1f49a23396","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:37.342719Z","signature_b64":"BD69VINaMnDMmJzo8gNj+B3IMfSkMkOhWk9OQwS04IsXAXxAlFP6RvWnsAAEgldw9FU36oYUd6dV+NP8eG0PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8b90ef86636313000667bf5370c2c4d7804cbae3b33795258a42a1f49a23396","last_reissued_at":"2026-07-05T03:46:37.342116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:37.342116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08176","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bN9extu5D5AjtHcBogXS7m5AH5cZy9uIeBplslpA8667HPSwmVNtSK2vJ6xxM+oheDxM746Szi1+t0ci+vnSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:00:28.098016Z"},"content_sha256":"310428b61e135d6f52e86d7c092c23565e4fca403d8ac21c5ff27dc92024f2b4","schema_version":"1.0","event_id":"sha256:310428b61e135d6f52e86d7c092c23565e4fca403d8ac21c5ff27dc92024f2b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VC4Q56DGGYYTAADGPP2TODBMJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collaborating with Humans without Human Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.MA"],"primary_cat":"cs.LG","authors_text":"DJ Strouse, Edward Hughes, Kevin R. McKee, Matt Botvinick, Richard Everett","submitted_at":"2021-10-15T16:03:57Z","abstract_excerpt":"Collaborating with humans requires rapidly adapting to their individual strengths, weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement learning techniques, such as self-play (SP) or population play (PP), produce agents that overfit to their training partners and do not generalize well to humans. Alternatively, researchers can collect human data, train a human model using behavioral cloning, and then use that model to train \"human-aware\" agents (\"behavioral cloning play\", or BCP). While such an approach can improve the generalization of agents to new human co-pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08176","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/2110.08176/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":"2026-07-05T03:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9n4dc9wjBlSfIby2vv/G2e9DBdcrqMrDcYRW2YWdUXB1sCSOChABtixHN+ENLnk2szQIi4iNJU9wj66ubFqcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:00:28.098346Z"},"content_sha256":"58af5ea68fde3180cc14d08709c7352e03679c7fb03505b86a0925b91d034d15","schema_version":"1.0","event_id":"sha256:58af5ea68fde3180cc14d08709c7352e03679c7fb03505b86a0925b91d034d15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VC4Q56DGGYYTAADGPP2TODBMJV/bundle.json","state_url":"https://pith.science/pith/VC4Q56DGGYYTAADGPP2TODBMJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VC4Q56DGGYYTAADGPP2TODBMJV/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":"2026-08-18T15:00:28Z","links":{"resolver":"https://pith.science/pith/VC4Q56DGGYYTAADGPP2TODBMJV","bundle":"https://pith.science/pith/VC4Q56DGGYYTAADGPP2TODBMJV/bundle.json","state":"https://pith.science/pith/VC4Q56DGGYYTAADGPP2TODBMJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VC4Q56DGGYYTAADGPP2TODBMJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VC4Q56DGGYYTAADGPP2TODBMJV","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":"fcceef5e5ebea3cd27d9de266168fa25c43d44ed601c1ff631c923ef6d72a31b","cross_cats_sorted":["cs.HC","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T16:03:57Z","title_canon_sha256":"96365b622bc69f9539d0cca4fcda030a9497d1f61e6b8eda78036a7904c37cac"},"schema_version":"1.0","source":{"id":"2110.08176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08176","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08176v2","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08176","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"VC4Q56DGGYYT","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"VC4Q56DGGYYTAADG","created_at":"2026-07-05T03:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"VC4Q56DG","created_at":"2026-07-05T03:46:37Z"}],"graph_snapshots":[{"event_id":"sha256:58af5ea68fde3180cc14d08709c7352e03679c7fb03505b86a0925b91d034d15","target":"graph","created_at":"2026-07-05T03:46:37Z","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/2110.08176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collaborating with humans requires rapidly adapting to their individual strengths, weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement learning techniques, such as self-play (SP) or population play (PP), produce agents that overfit to their training partners and do not generalize well to humans. Alternatively, researchers can collect human data, train a human model using behavioral cloning, and then use that model to train \"human-aware\" agents (\"behavioral cloning play\", or BCP). While such an approach can improve the generalization of agents to new human co-pla","authors_text":"DJ Strouse, Edward Hughes, Kevin R. McKee, Matt Botvinick, Richard Everett","cross_cats":["cs.HC","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T16:03:57Z","title":"Collaborating with Humans without Human Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08176","kind":"arxiv","version":2},"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":"sha256:310428b61e135d6f52e86d7c092c23565e4fca403d8ac21c5ff27dc92024f2b4","target":"record","created_at":"2026-07-05T03:46:37Z","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":"fcceef5e5ebea3cd27d9de266168fa25c43d44ed601c1ff631c923ef6d72a31b","cross_cats_sorted":["cs.HC","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T16:03:57Z","title_canon_sha256":"96365b622bc69f9539d0cca4fcda030a9497d1f61e6b8eda78036a7904c37cac"},"schema_version":"1.0","source":{"id":"2110.08176","kind":"arxiv","version":2}},"canonical_sha256":"a8b90ef86636313000667bf5370c2c4d7804cbae3b33795258a42a1f49a23396","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8b90ef86636313000667bf5370c2c4d7804cbae3b33795258a42a1f49a23396","first_computed_at":"2026-07-05T03:46:37.342116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:37.342116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BD69VINaMnDMmJzo8gNj+B3IMfSkMkOhWk9OQwS04IsXAXxAlFP6RvWnsAAEgldw9FU36oYUd6dV+NP8eG0PDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:37.342719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:310428b61e135d6f52e86d7c092c23565e4fca403d8ac21c5ff27dc92024f2b4","sha256:58af5ea68fde3180cc14d08709c7352e03679c7fb03505b86a0925b91d034d15"],"state_sha256":"6a161c3263733d6da1534f82d6d64ded20ebe14de61dddd9b6ace96d2eea6908"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uQ2inEWq3bI6u5BmIe3OATV2ZENvrRfcbs+5eemNCsjoXzNdg/DK33gKkvOzfjaUn32xY1jaAnxfxehqiKppCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:00:28.101963Z","bundle_sha256":"c7711ea69ed8b215d9167be4e1394a16a2c7d8e3f45852ef442d462ddc3b357a"}}