{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HHX3QAVJXLW3KLP7WQ7NELWTOM","short_pith_number":"pith:HHX3QAVJ","canonical_record":{"source":{"id":"2507.23701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1ca107535ba7b38e237ace3352f7b369bccdf29a281edb81402ce5e657a7088c","abstract_canon_sha256":"9555ccf4433033a5d4aaa1b267420bb86c4c5a718066ead7254b103d010a5c5b"},"schema_version":"1.0"},"canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","source":{"kind":"arxiv","id":"2507.23701","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23701","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23701v3","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23701","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"HHX3QAVJXLW3","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"HHX3QAVJXLW3KLP7","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"HHX3QAVJ","created_at":"2026-07-05T11:53:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HHX3QAVJXLW3KLP7WQ7NELWTOM","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1ca107535ba7b38e237ace3352f7b369bccdf29a281edb81402ce5e657a7088c","abstract_canon_sha256":"9555ccf4433033a5d4aaa1b267420bb86c4c5a718066ead7254b103d010a5c5b"},"schema_version":"1.0"},"canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:28.157181Z","signature_b64":"LShPm3LK9mUNiCNjnOyzMNli3olRM0GwmxQY1fP+dmiQ5t53a2sNIzP41i/eENkkVYvkLs1sdTwvnI4ijog9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","last_reissued_at":"2026-07-05T11:53:28.156620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:28.156620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23701","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKLGfPY7SMdLh1rW/Q7gA/DEdbNszfST45J7KMGkQ1//bw+Kmy1c0bZBUbXJwVWSKah5ida/2Sd9B2tegrMuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:42:12.900276Z"},"content_sha256":"af90909879eacaa4a0f1dc4aebb100a99db3112e79e9a87cb1d5fa2003514eba","schema_version":"1.0","event_id":"sha256:af90909879eacaa4a0f1dc4aebb100a99db3112e79e9a87cb1d5fa2003514eba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HHX3QAVJXLW3KLP7WQ7NELWTOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TextQuests: How Good are LLMs at Text-Based Video Games?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Andy Zou, Dan Hendrycks, Long Phan, Mantas Mazeika","submitted_at":"2025-07-31T16:22:55Z","abstract_excerpt":"Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23701","kind":"arxiv","version":3},"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/2507.23701/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":"2026-07-05T11:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtxigHiAK+//ryTNXD6+QdHX8wGqRsaO6VO0CiyJQCbqYNgT6h+Vs8rQFXmN7G/Bic0cnF46aFLQ/G2xbkulDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:42:12.901751Z"},"content_sha256":"09c634fdaf894b82865f4a9eaf655808c595a9484f867c64c633e7a6589c0a69","schema_version":"1.0","event_id":"sha256:09c634fdaf894b82865f4a9eaf655808c595a9484f867c64c633e7a6589c0a69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/bundle.json","state_url":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/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":"2026-08-05T07:42:12Z","links":{"resolver":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM","bundle":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/bundle.json","state":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HHX3QAVJXLW3KLP7WQ7NELWTOM","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":"9555ccf4433033a5d4aaa1b267420bb86c4c5a718066ead7254b103d010a5c5b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","title_canon_sha256":"1ca107535ba7b38e237ace3352f7b369bccdf29a281edb81402ce5e657a7088c"},"schema_version":"1.0","source":{"id":"2507.23701","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23701","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23701v3","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23701","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"HHX3QAVJXLW3","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"HHX3QAVJXLW3KLP7","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"HHX3QAVJ","created_at":"2026-07-05T11:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:09c634fdaf894b82865f4a9eaf655808c595a9484f867c64c633e7a6589c0a69","target":"graph","created_at":"2026-07-05T11:53:28Z","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/2507.23701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suit","authors_text":"Andy Zou, Dan Hendrycks, Long Phan, Mantas Mazeika","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","title":"TextQuests: How Good are LLMs at Text-Based Video Games?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23701","kind":"arxiv","version":3},"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:af90909879eacaa4a0f1dc4aebb100a99db3112e79e9a87cb1d5fa2003514eba","target":"record","created_at":"2026-07-05T11:53:28Z","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":"9555ccf4433033a5d4aaa1b267420bb86c4c5a718066ead7254b103d010a5c5b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","title_canon_sha256":"1ca107535ba7b38e237ace3352f7b369bccdf29a281edb81402ce5e657a7088c"},"schema_version":"1.0","source":{"id":"2507.23701","kind":"arxiv","version":3}},"canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","first_computed_at":"2026-07-05T11:53:28.156620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:28.156620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LShPm3LK9mUNiCNjnOyzMNli3olRM0GwmxQY1fP+dmiQ5t53a2sNIzP41i/eENkkVYvkLs1sdTwvnI4ijog9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:28.157181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23701","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af90909879eacaa4a0f1dc4aebb100a99db3112e79e9a87cb1d5fa2003514eba","sha256:09c634fdaf894b82865f4a9eaf655808c595a9484f867c64c633e7a6589c0a69"],"state_sha256":"43438c097da762807555f7ae53369340758ab6719ef39f9cf1b9f024bcccf154"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l68SVCaqrACtvJ5UBZdDx5qHv1rtEpM7qjik80vXc4Un3hsfdnXsm3YNwtgSA5BrvKUEB6kspUxnDusagq/RAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:42:12.910708Z","bundle_sha256":"297c5d7bbbdd7d5d245d3d6c7ea78a49994c15e8243e7d2c19b8edea423f2d52"}}