{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F46A3J26B4EY7UGFABUCEJZU2F","short_pith_number":"pith:F46A3J26","schema_version":"1.0","canonical_sha256":"2f3c0da75e0f098fd0c50068222734d142e114287b81309fb8ccebc27b0b2d80","source":{"kind":"arxiv","id":"2110.07342","version":3},"attestation_state":"computed","paper":{"title":"FILM: Following Instructions in Language with Modular Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Devendra Singh Chaplot, Pradeep Ravikumar, Ruslan Salakhutdinov, So Yeon Min, Yonatan Bisk","submitted_at":"2021-10-12T16:40:01Z","abstract_excerpt":"Recent methods for embodied instruction following are typically trained end-to-end using imitation learning. This often requires the use of expert trajectories and low-level language instructions. Such approaches assume that neural states will integrate multimodal semantics to perform state tracking, building spatial memory, exploration, and long-term planning. In contrast, we propose a modular method with structured representations that (1) builds a semantic map of the scene and (2) performs exploration with a semantic search policy, to achieve the natural language goal. Our modular method ac"},"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":"2110.07342","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T16:40:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7191a80ea7150c0f1c3aff6ed3b6c729b5ac7098ee7691a9afd1dcc01bcd6330","abstract_canon_sha256":"f83a602c1e49643a832aa39ff69bad2b232fb9faf513c591f435eb52a2a6dc8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:00.174909Z","signature_b64":"+lsZdz88Ew9DrM2z/pYl5kRhaV8C8OTRBpUu+KKsGJWSJZkvrWNxjI2jfq6xRqFvUYQTY94mE8yzu8/5dqE1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f3c0da75e0f098fd0c50068222734d142e114287b81309fb8ccebc27b0b2d80","last_reissued_at":"2026-07-05T04:06:00.174547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:00.174547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FILM: Following Instructions in Language with Modular Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Devendra Singh Chaplot, Pradeep Ravikumar, Ruslan Salakhutdinov, So Yeon Min, Yonatan Bisk","submitted_at":"2021-10-12T16:40:01Z","abstract_excerpt":"Recent methods for embodied instruction following are typically trained end-to-end using imitation learning. This often requires the use of expert trajectories and low-level language instructions. Such approaches assume that neural states will integrate multimodal semantics to perform state tracking, building spatial memory, exploration, and long-term planning. In contrast, we propose a modular method with structured representations that (1) builds a semantic map of the scene and (2) performs exploration with a semantic search policy, to achieve the natural language goal. Our modular method ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07342","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/2110.07342/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":"2110.07342","created_at":"2026-07-05T04:06:00.174603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07342v3","created_at":"2026-07-05T04:06:00.174603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07342","created_at":"2026-07-05T04:06:00.174603+00:00"},{"alias_kind":"pith_short_12","alias_value":"F46A3J26B4EY","created_at":"2026-07-05T04:06:00.174603+00:00"},{"alias_kind":"pith_short_16","alias_value":"F46A3J26B4EY7UGF","created_at":"2026-07-05T04:06:00.174603+00:00"},{"alias_kind":"pith_short_8","alias_value":"F46A3J26","created_at":"2026-07-05T04:06:00.174603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24456","citing_title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25851","citing_title":"RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26788","citing_title":"ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04108","citing_title":"Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14902","citing_title":"ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F","json":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F.json","graph_json":"https://pith.science/api/pith-number/F46A3J26B4EY7UGFABUCEJZU2F/graph.json","events_json":"https://pith.science/api/pith-number/F46A3J26B4EY7UGFABUCEJZU2F/events.json","paper":"https://pith.science/paper/F46A3J26"},"agent_actions":{"view_html":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F","download_json":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F.json","view_paper":"https://pith.science/paper/F46A3J26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07342&json=true","fetch_graph":"https://pith.science/api/pith-number/F46A3J26B4EY7UGFABUCEJZU2F/graph.json","fetch_events":"https://pith.science/api/pith-number/F46A3J26B4EY7UGFABUCEJZU2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F/action/storage_attestation","attest_author":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F/action/author_attestation","sign_citation":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F/action/citation_signature","submit_replication":"https://pith.science/pith/F46A3J26B4EY7UGFABUCEJZU2F/action/replication_record"}},"created_at":"2026-07-05T04:06:00.174603+00:00","updated_at":"2026-07-05T04:06:00.174603+00:00"}