{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GRCHB77X4JXEU74NSORMDEJD44","short_pith_number":"pith:GRCHB77X","canonical_record":{"source":{"id":"1906.02671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-04-24T17:43:40Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"81dd7a2b2e0e96ed2de12c04ddfe03aa7eb06e085fdeb17e9772b4de9735bf29","abstract_canon_sha256":"861257e8b7f35213958fd22a9aea628330d164744f98ff5cf4aa75c66cb816fc"},"schema_version":"1.0"},"canonical_sha256":"344470fff7e26e4a7f8d93a2c19123e705a568e8136404cafc28ca3afdee1f14","source":{"kind":"arxiv","id":"1906.02671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02671","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02671v1","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02671","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"GRCHB77X4JXE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GRCHB77X4JXEU74N","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GRCHB77X","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GRCHB77X4JXEU74NSORMDEJD44","target":"record","payload":{"canonical_record":{"source":{"id":"1906.02671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-04-24T17:43:40Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"81dd7a2b2e0e96ed2de12c04ddfe03aa7eb06e085fdeb17e9772b4de9735bf29","abstract_canon_sha256":"861257e8b7f35213958fd22a9aea628330d164744f98ff5cf4aa75c66cb816fc"},"schema_version":"1.0"},"canonical_sha256":"344470fff7e26e4a7f8d93a2c19123e705a568e8136404cafc28ca3afdee1f14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:00.489267Z","signature_b64":"baOdjdg1td6Z2JXvPUtg7lD70zAJP1VSH0652NPToYW5Ka21IuGFwi47MegLCZ32uwCM63aggBvXXsXsb84EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"344470fff7e26e4a7f8d93a2c19123e705a568e8136404cafc28ca3afdee1f14","last_reissued_at":"2026-05-17T23:44:00.488777Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:00.488777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.02671","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":"2026-05-17T23:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GEc4iXs2g0LsDxbnneWuvZNpWLVf6jWqBBpXmQQZIvgtRpaCDPNMLTQ+XPjMvUOdpHf3OAxkM33wuKdrJJBwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:13:59.857359Z"},"content_sha256":"954860efe1683cf124b08cb5492840be776d3c6cc53fe43f938875d642c44da7","schema_version":"1.0","event_id":"sha256:954860efe1683cf124b08cb5492840be776d3c6cc53fe43f938875d642c44da7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GRCHB77X4JXEU74NSORMDEJD44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounding Natural Language Commands to StarCraft II Game States for Narration-Guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.MM","authors_text":"Ethan Stump, Garrett Warnell, Nicholas Waytowich, Sean L. Barton, Vernon Lawhern","submitted_at":"2019-04-24T17:43:40Z","abstract_excerpt":"While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of {\\em reward sparsity}. This is especially true for tasks such as training an agent to play StarCraft II, a real-time strategy game where reward is only given at the end of a game which is usually very long. While this problem can be addressed through reward shaping, such approaches typically require a human expert with specialized knowledge. Inspired by the vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02671","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":""},"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":"2026-05-17T23:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hiP9fLnC8DuBgvMKykOOlLlTXkdFJbYQl0c9T1TbDEVf5Bx+aox2zGQ4wRyq7XXKiQDDZTpyUQftr8KGAIIADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:13:59.857937Z"},"content_sha256":"e7a09899e1d410f93dca2c605887bef8de0b9418e6804f3100d39f3151f08ca2","schema_version":"1.0","event_id":"sha256:e7a09899e1d410f93dca2c605887bef8de0b9418e6804f3100d39f3151f08ca2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GRCHB77X4JXEU74NSORMDEJD44/bundle.json","state_url":"https://pith.science/pith/GRCHB77X4JXEU74NSORMDEJD44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GRCHB77X4JXEU74NSORMDEJD44/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":"2026-05-31T21:13:59Z","links":{"resolver":"https://pith.science/pith/GRCHB77X4JXEU74NSORMDEJD44","bundle":"https://pith.science/pith/GRCHB77X4JXEU74NSORMDEJD44/bundle.json","state":"https://pith.science/pith/GRCHB77X4JXEU74NSORMDEJD44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GRCHB77X4JXEU74NSORMDEJD44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GRCHB77X4JXEU74NSORMDEJD44","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":"861257e8b7f35213958fd22a9aea628330d164744f98ff5cf4aa75c66cb816fc","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-04-24T17:43:40Z","title_canon_sha256":"81dd7a2b2e0e96ed2de12c04ddfe03aa7eb06e085fdeb17e9772b4de9735bf29"},"schema_version":"1.0","source":{"id":"1906.02671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02671","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02671v1","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02671","created_at":"2026-05-17T23:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"GRCHB77X4JXE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GRCHB77X4JXEU74N","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GRCHB77X","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e7a09899e1d410f93dca2c605887bef8de0b9418e6804f3100d39f3151f08ca2","target":"graph","created_at":"2026-05-17T23:44:00Z","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"},"paper":{"abstract_excerpt":"While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of {\\em reward sparsity}. This is especially true for tasks such as training an agent to play StarCraft II, a real-time strategy game where reward is only given at the end of a game which is usually very long. While this problem can be addressed through reward shaping, such approaches typically require a human expert with specialized knowledge. Inspired by the vis","authors_text":"Ethan Stump, Garrett Warnell, Nicholas Waytowich, Sean L. Barton, Vernon Lawhern","cross_cats":["cs.CL","cs.LG","cs.NE","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-04-24T17:43:40Z","title":"Grounding Natural Language Commands to StarCraft II Game States for Narration-Guided Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02671","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":"sha256:954860efe1683cf124b08cb5492840be776d3c6cc53fe43f938875d642c44da7","target":"record","created_at":"2026-05-17T23:44:00Z","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":"861257e8b7f35213958fd22a9aea628330d164744f98ff5cf4aa75c66cb816fc","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-04-24T17:43:40Z","title_canon_sha256":"81dd7a2b2e0e96ed2de12c04ddfe03aa7eb06e085fdeb17e9772b4de9735bf29"},"schema_version":"1.0","source":{"id":"1906.02671","kind":"arxiv","version":1}},"canonical_sha256":"344470fff7e26e4a7f8d93a2c19123e705a568e8136404cafc28ca3afdee1f14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"344470fff7e26e4a7f8d93a2c19123e705a568e8136404cafc28ca3afdee1f14","first_computed_at":"2026-05-17T23:44:00.488777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:00.488777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"baOdjdg1td6Z2JXvPUtg7lD70zAJP1VSH0652NPToYW5Ka21IuGFwi47MegLCZ32uwCM63aggBvXXsXsb84EBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:00.489267Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:954860efe1683cf124b08cb5492840be776d3c6cc53fe43f938875d642c44da7","sha256:e7a09899e1d410f93dca2c605887bef8de0b9418e6804f3100d39f3151f08ca2"],"state_sha256":"8dc6f7ab814ba4c049072919addf98e86ccc7dc9f09716b5dc3d576d7e52f7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ryNLFAjDim2VNQaBYE5+CAbxfwQU4WpaSaCaIZAHGnYjT6L46P4Cre4VgG/MMGr4Zah51BSAPT3PtPD78MgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T21:13:59.861114Z","bundle_sha256":"3a4320fdf7428d1f4e07e82a8303e4a1bc3cc4958bb829260fca775367b4a1a5"}}