{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3OJIF3VRBNGFU4SV76CO5HIDYQ","short_pith_number":"pith:3OJIF3VR","canonical_record":{"source":{"id":"2004.02986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"67cbdbeb2651b6e08c2f453f00bc9e0b52288b8b34df887c10c2ed15fd863490","abstract_canon_sha256":"2cd646a79e12847d162af832830f1e59f949031cb469ab495d902c581fd88c9f"},"schema_version":"1.0"},"canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","source":{"kind":"arxiv","id":"2004.02986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02986","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02986v1","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02986","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"3OJIF3VRBNGF","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"3OJIF3VRBNGFU4SV","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"3OJIF3VR","created_at":"2026-07-05T00:53:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3OJIF3VRBNGFU4SV76CO5HIDYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"67cbdbeb2651b6e08c2f453f00bc9e0b52288b8b34df887c10c2ed15fd863490","abstract_canon_sha256":"2cd646a79e12847d162af832830f1e59f949031cb469ab495d902c581fd88c9f"},"schema_version":"1.0"},"canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:22.151781Z","signature_b64":"xAtunXaKCYjrPxYXCTdSVExS2QxGXakM+qAirr6sV+b/LoeZsjtXuWsQfSgB9mm6eOyAZOLJ/0OTwXFtRBM2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","last_reissued_at":"2026-07-05T00:53:22.151409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:22.151409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02986","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":"2026-07-05T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vgI6QPynMyX3kuMcOYEsR17bK0kJcYxNAdug1lvJbNhoi+tD1sbz2X1WBQgjDYizzl2lkZf4IbMQK5QuykJPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:17:24.765404Z"},"content_sha256":"ff4a8dd08e64376f05e7f596917074fbf57beeb0a1aa8d28de5a5f34c4514e3c","schema_version":"1.0","event_id":"sha256:ff4a8dd08e64376f05e7f596917074fbf57beeb0a1aa8d28de5a5f34c4514e3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3OJIF3VRBNGFU4SV76CO5HIDYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2020-04-06T20:24:33Z","abstract_excerpt":"Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dialogues or games. However, models that do not have direct access to their state are harder to train; when the only state access is via the medium of language, this can be particularly pronounced. We introduce a new model amenable to deep Q-learning that incorporates a Siamese neural network architecture and a novel refactoring of the Q-value function"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02986","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/2004.02986/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":"2026-07-05T00:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXXsjOeCjn6hjzH40A4oc7YchcJ5ff6yULC8ofCmLjBq8cNOVgIsXtV/Rbz9UhFVXZ9Xo6zXQ9+jYFY1+fo8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:17:24.765987Z"},"content_sha256":"18999fdfb83b468d7cd642173c913eac473e81d0a39a56332262656179dea13e","schema_version":"1.0","event_id":"sha256:18999fdfb83b468d7cd642173c913eac473e81d0a39a56332262656179dea13e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/bundle.json","state_url":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/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":"2026-08-05T12:17:24Z","links":{"resolver":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ","bundle":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/bundle.json","state":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3OJIF3VRBNGFU4SV76CO5HIDYQ","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":"2cd646a79e12847d162af832830f1e59f949031cb469ab495d902c581fd88c9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","title_canon_sha256":"67cbdbeb2651b6e08c2f453f00bc9e0b52288b8b34df887c10c2ed15fd863490"},"schema_version":"1.0","source":{"id":"2004.02986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02986","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02986v1","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02986","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"3OJIF3VRBNGF","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"3OJIF3VRBNGFU4SV","created_at":"2026-07-05T00:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"3OJIF3VR","created_at":"2026-07-05T00:53:22Z"}],"graph_snapshots":[{"event_id":"sha256:18999fdfb83b468d7cd642173c913eac473e81d0a39a56332262656179dea13e","target":"graph","created_at":"2026-07-05T00:53:22Z","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/2004.02986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dialogues or games. However, models that do not have direct access to their state are harder to train; when the only state access is via the medium of language, this can be particularly pronounced. We introduce a new model amenable to deep Q-learning that incorporates a Siamese neural network architecture and a novel refactoring of the Q-value function","authors_text":"Jonathan May, Xusen Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","title":"Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02986","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:ff4a8dd08e64376f05e7f596917074fbf57beeb0a1aa8d28de5a5f34c4514e3c","target":"record","created_at":"2026-07-05T00:53:22Z","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":"2cd646a79e12847d162af832830f1e59f949031cb469ab495d902c581fd88c9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","title_canon_sha256":"67cbdbeb2651b6e08c2f453f00bc9e0b52288b8b34df887c10c2ed15fd863490"},"schema_version":"1.0","source":{"id":"2004.02986","kind":"arxiv","version":1}},"canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","first_computed_at":"2026-07-05T00:53:22.151409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:22.151409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xAtunXaKCYjrPxYXCTdSVExS2QxGXakM+qAirr6sV+b/LoeZsjtXuWsQfSgB9mm6eOyAZOLJ/0OTwXFtRBM2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:22.151781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff4a8dd08e64376f05e7f596917074fbf57beeb0a1aa8d28de5a5f34c4514e3c","sha256:18999fdfb83b468d7cd642173c913eac473e81d0a39a56332262656179dea13e"],"state_sha256":"b384d4bec936a4ce85e9f984ac4ffa28a54fc62148295a2373264edce39a6abf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWoEKeP+JZZtYWp6atLa4tK7QhR1pxkiXZrW1cMuTiywTPd/bD8WtWlcD6UaJ0+QAFPptAif5RVWouLPP0HfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:17:24.777263Z","bundle_sha256":"fc225a5b07bc7ad0a4cdfb84d6efff4bd60548ab89d26d228b15bd8003d4414f"}}