{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DOUV6PUVHZFRSXDCNVUIFX53MI","short_pith_number":"pith:DOUV6PUV","canonical_record":{"source":{"id":"2606.19370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"532c67a92c9f7d6a150515d0f3178bdf1f8ba432c176aac2ed48f9240005abd0","abstract_canon_sha256":"b5523b733e2b7bd5081e062f8ddc1eeb283aec1c13e6a484da16ed7a6fb6e0ce"},"schema_version":"1.0"},"canonical_sha256":"1ba95f3e953e4b195c626d6882dfbb6232df4e0f83c323160140fb369faaa0a0","source":{"kind":"arxiv","id":"2606.19370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19370","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19370v1","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19370","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"DOUV6PUVHZFR","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"DOUV6PUVHZFRSXDC","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"DOUV6PUV","created_at":"2026-06-19T16:12:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DOUV6PUVHZFRSXDCNVUIFX53MI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"532c67a92c9f7d6a150515d0f3178bdf1f8ba432c176aac2ed48f9240005abd0","abstract_canon_sha256":"b5523b733e2b7bd5081e062f8ddc1eeb283aec1c13e6a484da16ed7a6fb6e0ce"},"schema_version":"1.0"},"canonical_sha256":"1ba95f3e953e4b195c626d6882dfbb6232df4e0f83c323160140fb369faaa0a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:23.377347Z","signature_b64":"dVQSKhGjpWwRlptbp3uAFSYLVzC002qb5/jAgeOhpj/NVrqBs8p1vWCbKaGfASCS0Lj0uHdDKG6VeYgEfb2rAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ba95f3e953e4b195c626d6882dfbb6232df4e0f83c323160140fb369faaa0a0","last_reissued_at":"2026-06-19T16:12:23.376990Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:23.376990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19370","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":"2026-06-19T16:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3lMI+HfC7aRQ//eM4zUTrms95D7Sytey4IIyA1qdrS5noADCPok7r0ppWnFdol5pBGuLOcAdAO450RppvRmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:48:44.886752Z"},"content_sha256":"4f6e191af4c35358e518ada9421253d7732673bcb54ee2a752027ecfb4ed293f","schema_version":"1.0","event_id":"sha256:4f6e191af4c35358e518ada9421253d7732673bcb54ee2a752027ecfb4ed293f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DOUV6PUVHZFRSXDCNVUIFX53MI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human-like autonomy emerges from self-play and a pinch of human data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Daphne Cornelisse, Eugene Vinitsky, Jaime Fern\\'andez Fisac, Julian Hunt, Kevin Joseph, Wa\\\"el Doulazmi, Zixu Zhang","submitted_at":"2026-06-11T19:16:53Z","abstract_excerpt":"Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19370","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/2606.19370/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":"2026-06-19T16:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cK4NNlDAb/nC5UAr3THdWQ3s+pjH7/oJoS6wPAoWovYC1HanQMSXjQ/3Q1kMkqiuad9bf/KYnSUUDy/sngpHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:48:44.887131Z"},"content_sha256":"c7280adae078409335248c92d2d765aec9019631002c8056220f01ddfd2c273a","schema_version":"1.0","event_id":"sha256:c7280adae078409335248c92d2d765aec9019631002c8056220f01ddfd2c273a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/bundle.json","state_url":"https://pith.science/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/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":"2026-06-28T17:48:44Z","links":{"resolver":"https://pith.science/pith/DOUV6PUVHZFRSXDCNVUIFX53MI","bundle":"https://pith.science/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/bundle.json","state":"https://pith.science/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DOUV6PUVHZFRSXDCNVUIFX53MI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DOUV6PUVHZFRSXDCNVUIFX53MI","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":"b5523b733e2b7bd5081e062f8ddc1eeb283aec1c13e6a484da16ed7a6fb6e0ce","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53Z","title_canon_sha256":"532c67a92c9f7d6a150515d0f3178bdf1f8ba432c176aac2ed48f9240005abd0"},"schema_version":"1.0","source":{"id":"2606.19370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19370","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19370v1","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19370","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"DOUV6PUVHZFR","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"DOUV6PUVHZFRSXDC","created_at":"2026-06-19T16:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"DOUV6PUV","created_at":"2026-06-19T16:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:c7280adae078409335248c92d2d765aec9019631002c8056220f01ddfd2c273a","target":"graph","created_at":"2026-06-19T16:12:23Z","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/2606.19370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, o","authors_text":"Daphne Cornelisse, Eugene Vinitsky, Jaime Fern\\'andez Fisac, Julian Hunt, Kevin Joseph, Wa\\\"el Doulazmi, Zixu Zhang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53Z","title":"Human-like autonomy emerges from self-play and a pinch of human data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19370","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":"sha256:4f6e191af4c35358e518ada9421253d7732673bcb54ee2a752027ecfb4ed293f","target":"record","created_at":"2026-06-19T16:12:23Z","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":"b5523b733e2b7bd5081e062f8ddc1eeb283aec1c13e6a484da16ed7a6fb6e0ce","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53Z","title_canon_sha256":"532c67a92c9f7d6a150515d0f3178bdf1f8ba432c176aac2ed48f9240005abd0"},"schema_version":"1.0","source":{"id":"2606.19370","kind":"arxiv","version":1}},"canonical_sha256":"1ba95f3e953e4b195c626d6882dfbb6232df4e0f83c323160140fb369faaa0a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ba95f3e953e4b195c626d6882dfbb6232df4e0f83c323160140fb369faaa0a0","first_computed_at":"2026-06-19T16:12:23.376990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:23.376990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVQSKhGjpWwRlptbp3uAFSYLVzC002qb5/jAgeOhpj/NVrqBs8p1vWCbKaGfASCS0Lj0uHdDKG6VeYgEfb2rAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:23.377347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f6e191af4c35358e518ada9421253d7732673bcb54ee2a752027ecfb4ed293f","sha256:c7280adae078409335248c92d2d765aec9019631002c8056220f01ddfd2c273a"],"state_sha256":"159a6fe38c307246b16616bd9d5fc14d3e9c400871d0d3f3d764188cfcf1d178"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJZEbEgFzBNKjQCdqRSthhBW6/9Ste6h8TP5fturGoJ7foVJQUwcQ+/MHhpL6XOuuofsTZ55zpG09QI1QQdTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:48:44.889277Z","bundle_sha256":"fa98dca281d863c9224f4146ef7ac191ce5f119fea3f43197ddbdff6ed8983b3"}}