{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QFANL3AJ5LDLIVGWJWMHHMHFCM","short_pith_number":"pith:QFANL3AJ","canonical_record":{"source":{"id":"2311.07687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T19:12:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9083711fc96d2dbb9b192a522e12bfd00196987e9618b221ca31bdcb9857a032","abstract_canon_sha256":"854ca0e455ff6003fa73c22c2ee0c03b7f8f45643202f71f2a2d06ebfed155d2"},"schema_version":"1.0"},"canonical_sha256":"8140d5ec09eac6b454d64d9873b0e51302a0e72e2a7525e6b80c9324e1dc133e","source":{"kind":"arxiv","id":"2311.07687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07687","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07687v1","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07687","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"QFANL3AJ5LDL","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"QFANL3AJ5LDLIVGW","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"QFANL3AJ","created_at":"2026-07-05T07:12:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QFANL3AJ5LDLIVGWJWMHHMHFCM","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T19:12:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9083711fc96d2dbb9b192a522e12bfd00196987e9618b221ca31bdcb9857a032","abstract_canon_sha256":"854ca0e455ff6003fa73c22c2ee0c03b7f8f45643202f71f2a2d06ebfed155d2"},"schema_version":"1.0"},"canonical_sha256":"8140d5ec09eac6b454d64d9873b0e51302a0e72e2a7525e6b80c9324e1dc133e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:22.372036Z","signature_b64":"+7Z3OXoTIE/A75NZaTUBo/EX78ow+XKO2ys9Ubc2arkvUIgymkW0oGDjxJeUSq5hbQcr1I+NoDpZbGfXh4bPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8140d5ec09eac6b454d64d9873b0e51302a0e72e2a7525e6b80c9324e1dc133e","last_reissued_at":"2026-07-05T07:12:22.371585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:22.371585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07687","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":"2026-07-05T07:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"auXUZr26K89Ptvj5HPSj+aNKqQYojZZr3ezZKh0IryLsiK2yaBTqjPE1KLP/aRE3UZAU+UNGFryEeekRLaPgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:54:43.287542Z"},"content_sha256":"99df0f57e953741fb9bb0d42f26362e429578f70c7a5f9ae4dfb4bd1244c88f1","schema_version":"1.0","event_id":"sha256:99df0f57e953741fb9bb0d42f26362e429578f70c7a5f9ae4dfb4bd1244c88f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QFANL3AJ5LDLIVGWJWMHHMHFCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arjun Vaithilingam Sudhakar, Janarthanan Rajendran, Prasanna Parthasarathi, Sarath Chandar","submitted_at":"2023-11-13T19:12:49Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 -- for action candidate recommendations to improve the performance in text games in Jericho without environment-provided actions. However, CALM adapts GPT-2 with annotated human gameplays and keeps the LLM fixed during the learning of the text based games. In this work, we explore and evaluate updating LLM used for candidate recommendation during the learning of the text based game as well to mitigate the reliance on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07687","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/2311.07687/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":"2026-07-05T07:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vWpZ2ZPYKkqk5OqE4J6NYCixnTh1nbqat4Xupnu38gtC0/Gbj1uHXBzYouwPQY0G6oEmshSLX3SOOmeZ7daqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:54:43.288097Z"},"content_sha256":"8d94cf1da994150db0d8dc0b42d7b4c3d46b8bc582b7bb95905345b4eca561c5","schema_version":"1.0","event_id":"sha256:8d94cf1da994150db0d8dc0b42d7b4c3d46b8bc582b7bb95905345b4eca561c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/bundle.json","state_url":"https://pith.science/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/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":"2026-08-11T14:54:43Z","links":{"resolver":"https://pith.science/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM","bundle":"https://pith.science/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/bundle.json","state":"https://pith.science/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFANL3AJ5LDLIVGWJWMHHMHFCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QFANL3AJ5LDLIVGWJWMHHMHFCM","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":"854ca0e455ff6003fa73c22c2ee0c03b7f8f45643202f71f2a2d06ebfed155d2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T19:12:49Z","title_canon_sha256":"9083711fc96d2dbb9b192a522e12bfd00196987e9618b221ca31bdcb9857a032"},"schema_version":"1.0","source":{"id":"2311.07687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07687","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07687v1","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07687","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"QFANL3AJ5LDL","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"QFANL3AJ5LDLIVGW","created_at":"2026-07-05T07:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"QFANL3AJ","created_at":"2026-07-05T07:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:8d94cf1da994150db0d8dc0b42d7b4c3d46b8bc582b7bb95905345b4eca561c5","target":"graph","created_at":"2026-07-05T07:12:22Z","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/2311.07687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 -- for action candidate recommendations to improve the performance in text games in Jericho without environment-provided actions. However, CALM adapts GPT-2 with annotated human gameplays and keeps the LLM fixed during the learning of the text based games. In this work, we explore and evaluate updating LLM used for candidate recommendation during the learning of the text based game as well to mitigate the reliance on th","authors_text":"Arjun Vaithilingam Sudhakar, Janarthanan Rajendran, Prasanna Parthasarathi, Sarath Chandar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T19:12:49Z","title":"Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07687","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":"sha256:99df0f57e953741fb9bb0d42f26362e429578f70c7a5f9ae4dfb4bd1244c88f1","target":"record","created_at":"2026-07-05T07:12:22Z","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":"854ca0e455ff6003fa73c22c2ee0c03b7f8f45643202f71f2a2d06ebfed155d2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T19:12:49Z","title_canon_sha256":"9083711fc96d2dbb9b192a522e12bfd00196987e9618b221ca31bdcb9857a032"},"schema_version":"1.0","source":{"id":"2311.07687","kind":"arxiv","version":1}},"canonical_sha256":"8140d5ec09eac6b454d64d9873b0e51302a0e72e2a7525e6b80c9324e1dc133e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8140d5ec09eac6b454d64d9873b0e51302a0e72e2a7525e6b80c9324e1dc133e","first_computed_at":"2026-07-05T07:12:22.371585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:22.371585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7Z3OXoTIE/A75NZaTUBo/EX78ow+XKO2ys9Ubc2arkvUIgymkW0oGDjxJeUSq5hbQcr1I+NoDpZbGfXh4bPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:22.372036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99df0f57e953741fb9bb0d42f26362e429578f70c7a5f9ae4dfb4bd1244c88f1","sha256:8d94cf1da994150db0d8dc0b42d7b4c3d46b8bc582b7bb95905345b4eca561c5"],"state_sha256":"daa49445f71840e7789da1d0d57962b09dd35aa0b711c8898951184c0e87303a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2vfV+ptfciNe6aaGrw6RFj/kBkAXtUUC0HtTP8d/xjSfVun+6kEOn2NCE5du6qLRSGpSkv+7PqXsoGEk1GeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:54:43.292824Z","bundle_sha256":"3e1cbf277d54fe591b647e5e2ee294e7b0b45f3d5270afd77f9bdb91c0bb536e"}}