{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YIE6UMCMFVZKOSY7NMC4FS4YJZ","short_pith_number":"pith:YIE6UMCM","schema_version":"1.0","canonical_sha256":"c209ea304c2d72a74b1f6b05c2cb984e4dcb67a6ecf6c29bfae14d60a917984c","source":{"kind":"arxiv","id":"1912.01734","version":2},"attestation_state":"computed","paper":{"title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Gordon, Dieter Fox, Jesse Thomason, Luke Zettlemoyer, Mohit Shridhar, Roozbeh Mottaghi, Winson Han, Yonatan Bisk","submitted_at":"2019-12-03T23:18:59Z","abstract_excerpt":"We present ALFRED (Action Learning From Realistic Environments and Directives), a benchmark for learning a mapping from natural language instructions and egocentric vision to sequences of actions for household tasks. ALFRED includes long, compositional tasks with non-reversible state changes to shrink the gap between research benchmarks and real-world applications. ALFRED consists of expert demonstrations in interactive visual environments for 25k natural language directives. These directives contain both high-level goals like \"Rinse off a mug and place it in the coffee maker.\" and low-level l"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.01734","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-03T23:18:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"07a0028fd6a0a10b98bd600b2177bf6e1198d5492dff3b097cfbf1cb9ea6db9b","abstract_canon_sha256":"06ccea90b7894084b7234a85179ae722ced70418b78d42dd8ccf0ba0ec974780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:35.161359Z","signature_b64":"5aPg87KiMN42JqsJGjbDUCbfXp/jHHT7okWD1mH2BAtNug/oQrozRe/BUYu5awDQRokLM9eDiFso9++ZtzCNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c209ea304c2d72a74b1f6b05c2cb984e4dcb67a6ecf6c29bfae14d60a917984c","last_reissued_at":"2026-07-05T00:51:35.160941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:35.160941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniel Gordon, Dieter Fox, Jesse Thomason, Luke Zettlemoyer, Mohit Shridhar, Roozbeh Mottaghi, Winson Han, Yonatan Bisk","submitted_at":"2019-12-03T23:18:59Z","abstract_excerpt":"We present ALFRED (Action Learning From Realistic Environments and Directives), a benchmark for learning a mapping from natural language instructions and egocentric vision to sequences of actions for household tasks. ALFRED includes long, compositional tasks with non-reversible state changes to shrink the gap between research benchmarks and real-world applications. ALFRED consists of expert demonstrations in interactive visual environments for 25k natural language directives. These directives contain both high-level goals like \"Rinse off a mug and place it in the coffee maker.\" and low-level l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01734","kind":"arxiv","version":2},"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/1912.01734/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.01734","created_at":"2026-07-05T00:51:35.160996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01734v2","created_at":"2026-07-05T00:51:35.160996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01734","created_at":"2026-07-05T00:51:35.160996+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIE6UMCMFVZK","created_at":"2026-07-05T00:51:35.160996+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIE6UMCMFVZKOSY7","created_at":"2026-07-05T00:51:35.160996+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIE6UMCM","created_at":"2026-07-05T00:51:35.160996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01901","citing_title":"The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13716","citing_title":"SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11436","citing_title":"Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ","json":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ.json","graph_json":"https://pith.science/api/pith-number/YIE6UMCMFVZKOSY7NMC4FS4YJZ/graph.json","events_json":"https://pith.science/api/pith-number/YIE6UMCMFVZKOSY7NMC4FS4YJZ/events.json","paper":"https://pith.science/paper/YIE6UMCM"},"agent_actions":{"view_html":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ","download_json":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ.json","view_paper":"https://pith.science/paper/YIE6UMCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01734&json=true","fetch_graph":"https://pith.science/api/pith-number/YIE6UMCMFVZKOSY7NMC4FS4YJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YIE6UMCMFVZKOSY7NMC4FS4YJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ/action/storage_attestation","attest_author":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ/action/author_attestation","sign_citation":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ/action/citation_signature","submit_replication":"https://pith.science/pith/YIE6UMCMFVZKOSY7NMC4FS4YJZ/action/replication_record"}},"created_at":"2026-07-05T00:51:35.160996+00:00","updated_at":"2026-07-05T00:51:35.160996+00:00"}