{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:VBPNKQWTCET2AMRJ36JW5HYKMK","short_pith_number":"pith:VBPNKQWT","canonical_record":{"source":{"id":"2011.14124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-28T12:37:02Z","cross_cats_sorted":[],"title_canon_sha256":"d0f9ea81d48a3d09c257bd196f84696c8129221d04d54f86253872e33e0a6304","abstract_canon_sha256":"7ecf7cbbc5e8e5925df845ba6af70981a0c4179c013bab1b478000c77d953c90"},"schema_version":"1.0"},"canonical_sha256":"a85ed542d31127a03229df936e9f0a629a5372e61c58d41d527ddb3db005638a","source":{"kind":"arxiv","id":"2011.14124","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14124","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14124v1","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14124","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_12","alias_value":"VBPNKQWTCET2","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_16","alias_value":"VBPNKQWTCET2AMRJ","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_8","alias_value":"VBPNKQWT","created_at":"2026-07-05T01:55:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:VBPNKQWTCET2AMRJ36JW5HYKMK","target":"record","payload":{"canonical_record":{"source":{"id":"2011.14124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-28T12:37:02Z","cross_cats_sorted":[],"title_canon_sha256":"d0f9ea81d48a3d09c257bd196f84696c8129221d04d54f86253872e33e0a6304","abstract_canon_sha256":"7ecf7cbbc5e8e5925df845ba6af70981a0c4179c013bab1b478000c77d953c90"},"schema_version":"1.0"},"canonical_sha256":"a85ed542d31127a03229df936e9f0a629a5372e61c58d41d527ddb3db005638a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:17.513849Z","signature_b64":"suOkE+oLoSqUJZKwEtR/zku2FiicHroMzv2Z+M00lhZUwDjxb7LSgiw6H12/yK9w+NuuJchNd8eIGG7MBIbnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85ed542d31127a03229df936e9f0a629a5372e61c58d41d527ddb3db005638a","last_reissued_at":"2026-07-05T01:55:17.513440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:17.513440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.14124","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:55:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JaMhPiwfbIq38q0ArOibNxvuYozBQZqoKzIb2WxiqjtOct1NE9SdcIxyrNsAZbVqLUsfM7YW3hWnRmp2mJm/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:15.070851Z"},"content_sha256":"c00d529109b2c443ee6162a75e060f0342e4482fb527149d0e66cf635e6fb6d8","schema_version":"1.0","event_id":"sha256:c00d529109b2c443ee6162a75e060f0342e4482fb527149d0e66cf635e6fb6d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:VBPNKQWTCET2AMRJ36JW5HYKMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-Agent Cooperation in Bridge Bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Edward Lockhart, Lucas Smaira, Neil Burch, Nolan Bard, Ray Smith, Sebastian Borgeaud, Tom Eccles","submitted_at":"2020-11-28T12:37:02Z","abstract_excerpt":"We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation. Our learning approach consists of imitation learning, search, and policy iteration. Our trained agents achieve a new state-of-the-art for bridge bidding in three settings: an agent playing in partnership with a copy of itself; an agent partnering a pre-existing bot; and an agent partnering a human player."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14124","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/2011.14124/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":"2026-07-05T01:55:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R/vYHmLHC4VFwNKUwmpi4bp8P8qEMpXIS9UCp8Yl2cTRI1aJO6kGwQ2Ie47kj74P89JH4LW8yCJASEM0UG0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:15.071217Z"},"content_sha256":"8317a13c4da7ed9f85495f1b797dadada04287b8aa936292243bf6e954a2b6b4","schema_version":"1.0","event_id":"sha256:8317a13c4da7ed9f85495f1b797dadada04287b8aa936292243bf6e954a2b6b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/bundle.json","state_url":"https://pith.science/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/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":"2026-07-07T14:06:15Z","links":{"resolver":"https://pith.science/pith/VBPNKQWTCET2AMRJ36JW5HYKMK","bundle":"https://pith.science/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/bundle.json","state":"https://pith.science/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBPNKQWTCET2AMRJ36JW5HYKMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VBPNKQWTCET2AMRJ36JW5HYKMK","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":"7ecf7cbbc5e8e5925df845ba6af70981a0c4179c013bab1b478000c77d953c90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-28T12:37:02Z","title_canon_sha256":"d0f9ea81d48a3d09c257bd196f84696c8129221d04d54f86253872e33e0a6304"},"schema_version":"1.0","source":{"id":"2011.14124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14124","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14124v1","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14124","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_12","alias_value":"VBPNKQWTCET2","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_16","alias_value":"VBPNKQWTCET2AMRJ","created_at":"2026-07-05T01:55:17Z"},{"alias_kind":"pith_short_8","alias_value":"VBPNKQWT","created_at":"2026-07-05T01:55:17Z"}],"graph_snapshots":[{"event_id":"sha256:8317a13c4da7ed9f85495f1b797dadada04287b8aa936292243bf6e954a2b6b4","target":"graph","created_at":"2026-07-05T01:55:17Z","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/2011.14124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation. Our learning approach consists of imitation learning, search, and policy iteration. Our trained agents achieve a new state-of-the-art for bridge bidding in three settings: an agent playing in partnership with a copy of itself; an agent partnering a pre-existing bot; and an agent partnering a human player.","authors_text":"Edward Lockhart, Lucas Smaira, Neil Burch, Nolan Bard, Ray Smith, Sebastian Borgeaud, Tom Eccles","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-28T12:37:02Z","title":"Human-Agent Cooperation in Bridge Bidding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14124","kind":"arxiv","version":1},"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:c00d529109b2c443ee6162a75e060f0342e4482fb527149d0e66cf635e6fb6d8","target":"record","created_at":"2026-07-05T01:55:17Z","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":"7ecf7cbbc5e8e5925df845ba6af70981a0c4179c013bab1b478000c77d953c90","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-11-28T12:37:02Z","title_canon_sha256":"d0f9ea81d48a3d09c257bd196f84696c8129221d04d54f86253872e33e0a6304"},"schema_version":"1.0","source":{"id":"2011.14124","kind":"arxiv","version":1}},"canonical_sha256":"a85ed542d31127a03229df936e9f0a629a5372e61c58d41d527ddb3db005638a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a85ed542d31127a03229df936e9f0a629a5372e61c58d41d527ddb3db005638a","first_computed_at":"2026-07-05T01:55:17.513440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:17.513440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"suOkE+oLoSqUJZKwEtR/zku2FiicHroMzv2Z+M00lhZUwDjxb7LSgiw6H12/yK9w+NuuJchNd8eIGG7MBIbnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:17.513849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c00d529109b2c443ee6162a75e060f0342e4482fb527149d0e66cf635e6fb6d8","sha256:8317a13c4da7ed9f85495f1b797dadada04287b8aa936292243bf6e954a2b6b4"],"state_sha256":"2537945fa595b523211ac197a3ffff963c40103f9dafa11c6b0b2ca981c3508a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKo3Rst0IwMVNu2BoBaXozpY9F701yo6t4uNFdtqqord5pnPxrz3vLODoxlEDQ9753QHjGeCoLDDSoJF+XSNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:06:15.073124Z","bundle_sha256":"693fe370cd5e53139770f371724c773867f6d587c754c9d0ea99ea6a344beb66"}}