{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4RNRRESWCPHPTZRU2RV722I7J7","short_pith_number":"pith:4RNRRESW","canonical_record":{"source":{"id":"2205.13079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T23:07:10Z","cross_cats_sorted":[],"title_canon_sha256":"20e38a2110eee26677e01a2a963e8d57b3ce2b32dd41da94e4db42f4bde2ddfd","abstract_canon_sha256":"e282e6e40a32a1d66cc5ddc020f39c3399ef0fc31384884518b6c2c711d1a371"},"schema_version":"1.0"},"canonical_sha256":"e45b18925613cef9e634d46bfd691f4fe5e5c3cb1891adfc5835db399d8b7e2e","source":{"kind":"arxiv","id":"2205.13079","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13079","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13079v1","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13079","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"4RNRRESWCPHP","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"4RNRRESWCPHPTZRU","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"4RNRRESW","created_at":"2026-07-05T04:26:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4RNRRESWCPHPTZRU2RV722I7J7","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T23:07:10Z","cross_cats_sorted":[],"title_canon_sha256":"20e38a2110eee26677e01a2a963e8d57b3ce2b32dd41da94e4db42f4bde2ddfd","abstract_canon_sha256":"e282e6e40a32a1d66cc5ddc020f39c3399ef0fc31384884518b6c2c711d1a371"},"schema_version":"1.0"},"canonical_sha256":"e45b18925613cef9e634d46bfd691f4fe5e5c3cb1891adfc5835db399d8b7e2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:39.655900Z","signature_b64":"GIKRBvbpfOj+8NACOMhSZ4rELBWdlVPwPCKSth9Yr0AK6Xa17rQ3ZMybNnQuyZgel0362N5IaODYldUgJdyPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e45b18925613cef9e634d46bfd691f4fe5e5c3cb1891adfc5835db399d8b7e2e","last_reissued_at":"2026-07-05T04:26:39.655522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:39.655522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13079","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":"2026-07-05T04:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+SZ2utWDTQzyaVydFO/3N/xO0NFedfWRPVfpPjaaHjQLeraEBcf6GvPyYMXyMsyID06mWz+3g7FRttlF6Y9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:26:44.162035Z"},"content_sha256":"a442fec35835604b8af0d88dcaca06458152ac57943f39af7e22c7ccd4df6f01","schema_version":"1.0","event_id":"sha256:a442fec35835604b8af0d88dcaca06458152ac57943f39af7e22c7ccd4df6f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4RNRRESWCPHPTZRU2RV722I7J7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Query Internet Text for Informing Reinforcement Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alekhya Pyla, Kolby Nottingham, Roy Fox, Sameer Singh","submitted_at":"2022-05-25T23:07:10Z","abstract_excerpt":"Generalization to out of distribution tasks in reinforcement learning is a challenging problem. One successful approach improves generalization by conditioning policies on task or environment descriptions that provide information about the current transition or reward functions. Previously, these descriptions were often expressed as generated or crowd sourced text. In this work, we begin to tackle the problem of extracting useful information from natural language found in the wild (e.g. internet forums, documentation, and wikis). These natural, pre-existing sources are especially challenging, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13079","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/2205.13079/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":"2026-07-05T04:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/bcgrKuSSVoedQ/7SEl5D7mB78yUNsQEOHunFP9LUPri7Ic0rgwOTHo7sOhtwinrXMm+hYfW5a2C0T+SVubDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T12:26:44.162589Z"},"content_sha256":"9155098eaa60357f890ca70509d21d90c2fba27662a7787cf413bf17af170ef1","schema_version":"1.0","event_id":"sha256:9155098eaa60357f890ca70509d21d90c2fba27662a7787cf413bf17af170ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RNRRESWCPHPTZRU2RV722I7J7/bundle.json","state_url":"https://pith.science/pith/4RNRRESWCPHPTZRU2RV722I7J7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RNRRESWCPHPTZRU2RV722I7J7/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":"2026-08-22T12:26:44Z","links":{"resolver":"https://pith.science/pith/4RNRRESWCPHPTZRU2RV722I7J7","bundle":"https://pith.science/pith/4RNRRESWCPHPTZRU2RV722I7J7/bundle.json","state":"https://pith.science/pith/4RNRRESWCPHPTZRU2RV722I7J7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RNRRESWCPHPTZRU2RV722I7J7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4RNRRESWCPHPTZRU2RV722I7J7","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":"e282e6e40a32a1d66cc5ddc020f39c3399ef0fc31384884518b6c2c711d1a371","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T23:07:10Z","title_canon_sha256":"20e38a2110eee26677e01a2a963e8d57b3ce2b32dd41da94e4db42f4bde2ddfd"},"schema_version":"1.0","source":{"id":"2205.13079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13079","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13079v1","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13079","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"4RNRRESWCPHP","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"4RNRRESWCPHPTZRU","created_at":"2026-07-05T04:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"4RNRRESW","created_at":"2026-07-05T04:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:9155098eaa60357f890ca70509d21d90c2fba27662a7787cf413bf17af170ef1","target":"graph","created_at":"2026-07-05T04:26:39Z","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/2205.13079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalization to out of distribution tasks in reinforcement learning is a challenging problem. One successful approach improves generalization by conditioning policies on task or environment descriptions that provide information about the current transition or reward functions. Previously, these descriptions were often expressed as generated or crowd sourced text. In this work, we begin to tackle the problem of extracting useful information from natural language found in the wild (e.g. internet forums, documentation, and wikis). These natural, pre-existing sources are especially challenging, ","authors_text":"Alekhya Pyla, Kolby Nottingham, Roy Fox, Sameer Singh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T23:07:10Z","title":"Learning to Query Internet Text for Informing Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13079","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:a442fec35835604b8af0d88dcaca06458152ac57943f39af7e22c7ccd4df6f01","target":"record","created_at":"2026-07-05T04:26:39Z","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":"e282e6e40a32a1d66cc5ddc020f39c3399ef0fc31384884518b6c2c711d1a371","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T23:07:10Z","title_canon_sha256":"20e38a2110eee26677e01a2a963e8d57b3ce2b32dd41da94e4db42f4bde2ddfd"},"schema_version":"1.0","source":{"id":"2205.13079","kind":"arxiv","version":1}},"canonical_sha256":"e45b18925613cef9e634d46bfd691f4fe5e5c3cb1891adfc5835db399d8b7e2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e45b18925613cef9e634d46bfd691f4fe5e5c3cb1891adfc5835db399d8b7e2e","first_computed_at":"2026-07-05T04:26:39.655522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:39.655522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GIKRBvbpfOj+8NACOMhSZ4rELBWdlVPwPCKSth9Yr0AK6Xa17rQ3ZMybNnQuyZgel0362N5IaODYldUgJdyPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:39.655900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a442fec35835604b8af0d88dcaca06458152ac57943f39af7e22c7ccd4df6f01","sha256:9155098eaa60357f890ca70509d21d90c2fba27662a7787cf413bf17af170ef1"],"state_sha256":"9ee81df53125c22eb6c8c022e6bd3e763a9594c66a552f953612a8064bc5c8dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDaSY5c+i5uZ8sqLovhSLS0VTqAJK62YE8PptIQ+cmuiPYtPA7BxkK0XjBks7Ay0iPzQ9ClohcY1a+Y4nospCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T12:26:44.166532Z","bundle_sha256":"409f62f60d2cc95bf8d16299e007f23c4a336dd7f733377b53a6b30b83ca24b1"}}