{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NQDXQMU7YQH2I3TEW4HVOMI2AC","short_pith_number":"pith:NQDXQMU7","canonical_record":{"source":{"id":"2001.05994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-16T18:51:42Z","cross_cats_sorted":["cs.MA","cs.RO"],"title_canon_sha256":"919019780cd572e8ae71e6243bc71ba2413e8ec789df3f309690a3c382462a61","abstract_canon_sha256":"24fca6c60cf79f589cc6abf7e7aefa7bec0cdaa330c145e5691a61b4a633480e"},"schema_version":"1.0"},"canonical_sha256":"6c0778329fc40fa46e64b70f57311a00af750b5aba8cb6e960ce7ec7d7239211","source":{"kind":"arxiv","id":"2001.05994","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05994","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05994v2","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05994","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"NQDXQMU7YQH2","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"NQDXQMU7YQH2I3TE","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"NQDXQMU7","created_at":"2026-07-05T01:41:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NQDXQMU7YQH2I3TEW4HVOMI2AC","target":"record","payload":{"canonical_record":{"source":{"id":"2001.05994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-16T18:51:42Z","cross_cats_sorted":["cs.MA","cs.RO"],"title_canon_sha256":"919019780cd572e8ae71e6243bc71ba2413e8ec789df3f309690a3c382462a61","abstract_canon_sha256":"24fca6c60cf79f589cc6abf7e7aefa7bec0cdaa330c145e5691a61b4a633480e"},"schema_version":"1.0"},"canonical_sha256":"6c0778329fc40fa46e64b70f57311a00af750b5aba8cb6e960ce7ec7d7239211","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:16.369566Z","signature_b64":"aLiVR7jumGmPp8bdfFpHg/nNsA4bLexCwHFtEvt1dFZ1L6tEB0SyIcLj7A35YXXFjkrdHPNLlgMzQijPHwUWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c0778329fc40fa46e64b70f57311a00af750b5aba8cb6e960ce7ec7d7239211","last_reissued_at":"2026-07-05T01:41:16.369190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:16.369190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.05994","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":"2026-07-05T01:41:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qoracOW8GnG24iHA5vko0dOjhh7CvUxH2fdUs3UDav3139EKn/Hh2UYIEaBBtczFWVQsQnzz0vEm/tW6mO0cAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:18:52.580898Z"},"content_sha256":"e1a7156fa9a830155d04ef2c0b38d5ce7206147dc29442943e46a2210aac4a48","schema_version":"1.0","event_id":"sha256:e1a7156fa9a830155d04ef2c0b38d5ce7206147dc29442943e46a2210aac4a48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NQDXQMU7YQH2I3TEW4HVOMI2AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarially Guided Self-Play for Adopting Social Conventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Julie Shah, Mycal Tucker, Yilun Zhou","submitted_at":"2020-01-16T18:51:42Z","abstract_excerpt":"Robotic agents must adopt existing social conventions in order to be effective teammates. These social conventions, such as driving on the right or left side of the road, are arbitrary choices among optimal policies, but all agents on a successful team must use the same convention. Prior work has identified a method of combining self-play with paired input-output data gathered from existing agents in order to learn their social convention without interacting with them. We build upon this work by introducing a technique called Adversarial Self-Play (ASP) that uses adversarial training to shape "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05994","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/2001.05994/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":"2026-07-05T01:41:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXubOTdT0Is4A0y3+7UvYE4zCOe3prVnwii/sec+7jXwR1ycZsuUXjxNAFDbNCnZY5g/RXdmJF7f2fIWS6jRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:18:52.581418Z"},"content_sha256":"3394ac99c15f3ceeec137631a11482b0525e4f41a207e1fd876b8a354fb209e8","schema_version":"1.0","event_id":"sha256:3394ac99c15f3ceeec137631a11482b0525e4f41a207e1fd876b8a354fb209e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/bundle.json","state_url":"https://pith.science/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/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":"2026-08-07T07:18:52Z","links":{"resolver":"https://pith.science/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC","bundle":"https://pith.science/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/bundle.json","state":"https://pith.science/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQDXQMU7YQH2I3TEW4HVOMI2AC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NQDXQMU7YQH2I3TEW4HVOMI2AC","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":"24fca6c60cf79f589cc6abf7e7aefa7bec0cdaa330c145e5691a61b4a633480e","cross_cats_sorted":["cs.MA","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-16T18:51:42Z","title_canon_sha256":"919019780cd572e8ae71e6243bc71ba2413e8ec789df3f309690a3c382462a61"},"schema_version":"1.0","source":{"id":"2001.05994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05994","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05994v2","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05994","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"NQDXQMU7YQH2","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"NQDXQMU7YQH2I3TE","created_at":"2026-07-05T01:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"NQDXQMU7","created_at":"2026-07-05T01:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:3394ac99c15f3ceeec137631a11482b0525e4f41a207e1fd876b8a354fb209e8","target":"graph","created_at":"2026-07-05T01:41:16Z","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/2001.05994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robotic agents must adopt existing social conventions in order to be effective teammates. These social conventions, such as driving on the right or left side of the road, are arbitrary choices among optimal policies, but all agents on a successful team must use the same convention. Prior work has identified a method of combining self-play with paired input-output data gathered from existing agents in order to learn their social convention without interacting with them. We build upon this work by introducing a technique called Adversarial Self-Play (ASP) that uses adversarial training to shape ","authors_text":"Julie Shah, Mycal Tucker, Yilun Zhou","cross_cats":["cs.MA","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-16T18:51:42Z","title":"Adversarially Guided Self-Play for Adopting Social Conventions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05994","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:e1a7156fa9a830155d04ef2c0b38d5ce7206147dc29442943e46a2210aac4a48","target":"record","created_at":"2026-07-05T01:41:16Z","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":"24fca6c60cf79f589cc6abf7e7aefa7bec0cdaa330c145e5691a61b4a633480e","cross_cats_sorted":["cs.MA","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-16T18:51:42Z","title_canon_sha256":"919019780cd572e8ae71e6243bc71ba2413e8ec789df3f309690a3c382462a61"},"schema_version":"1.0","source":{"id":"2001.05994","kind":"arxiv","version":2}},"canonical_sha256":"6c0778329fc40fa46e64b70f57311a00af750b5aba8cb6e960ce7ec7d7239211","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c0778329fc40fa46e64b70f57311a00af750b5aba8cb6e960ce7ec7d7239211","first_computed_at":"2026-07-05T01:41:16.369190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:16.369190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aLiVR7jumGmPp8bdfFpHg/nNsA4bLexCwHFtEvt1dFZ1L6tEB0SyIcLj7A35YXXFjkrdHPNLlgMzQijPHwUWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:16.369566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1a7156fa9a830155d04ef2c0b38d5ce7206147dc29442943e46a2210aac4a48","sha256:3394ac99c15f3ceeec137631a11482b0525e4f41a207e1fd876b8a354fb209e8"],"state_sha256":"39734d3d12f5447ddcfedb1325a3b36fbba593b70383560624c2b4991487f30e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28u86Xv4tj630n0kjdfD5lSDjte09m3PmQr8r323DC1DMVcEdykizl+p3xJzeCkAHDr7jDFxbg4HY94J21xJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:18:52.585786Z","bundle_sha256":"f35552485229d01bfec93ac2d949a722cefe09838be3e6895e0048830de05ff4"}}