{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A5XBTMKRABGDDAKGZQCTLJ2NDX","short_pith_number":"pith:A5XBTMKR","schema_version":"1.0","canonical_sha256":"076e19b151004c318146cc0535a74d1dec89ca4bfde979c30a0588e934969a6a","source":{"kind":"arxiv","id":"2101.07891","version":1},"attestation_state":"computed","paper":{"title":"A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fateme Fotouhif, Homagni Saha, Qisai Liu, Soumik Sarkar","submitted_at":"2021-01-19T23:05:43Z","abstract_excerpt":"In this paper we propose a new framework - MoViLan (Modular Vision and Language) for execution of visually grounded natural language instructions for day to day indoor household tasks. While several data-driven, end-to-end learning frameworks have been proposed for targeted navigation tasks based on the vision and language modalities, performance on recent benchmark data sets revealed the gap in developing comprehensive techniques for long horizon, compositional tasks (involving manipulation and navigation) with diverse object categories, realistic instructions and visual scenarios with non-re"},"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":"2101.07891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-19T23:05:43Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"c979138920ec2e9ef88ee17d05a9d7ae767368ec246a59b2308b8b476cd77054","abstract_canon_sha256":"4a2042c371ce6c3cfde60803b6d6507b32cdae4f321a3e452aa080e196ab9a9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:22.944482Z","signature_b64":"DvDanvJhbWGDp6pYOm69TKe356cMq1vT05vHeHOa5IqprXT/OwTaA2K+QOx2dlHtRAljnhlBlxiEjokRIaFWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076e19b151004c318146cc0535a74d1dec89ca4bfde979c30a0588e934969a6a","last_reissued_at":"2026-07-05T02:08:22.944072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:22.944072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fateme Fotouhif, Homagni Saha, Qisai Liu, Soumik Sarkar","submitted_at":"2021-01-19T23:05:43Z","abstract_excerpt":"In this paper we propose a new framework - MoViLan (Modular Vision and Language) for execution of visually grounded natural language instructions for day to day indoor household tasks. While several data-driven, end-to-end learning frameworks have been proposed for targeted navigation tasks based on the vision and language modalities, performance on recent benchmark data sets revealed the gap in developing comprehensive techniques for long horizon, compositional tasks (involving manipulation and navigation) with diverse object categories, realistic instructions and visual scenarios with non-re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07891","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/2101.07891/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":"2101.07891","created_at":"2026-07-05T02:08:22.944135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07891v1","created_at":"2026-07-05T02:08:22.944135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07891","created_at":"2026-07-05T02:08:22.944135+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5XBTMKRABGD","created_at":"2026-07-05T02:08:22.944135+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5XBTMKRABGDDAKG","created_at":"2026-07-05T02:08:22.944135+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5XBTMKR","created_at":"2026-07-05T02:08:22.944135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX","json":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX.json","graph_json":"https://pith.science/api/pith-number/A5XBTMKRABGDDAKGZQCTLJ2NDX/graph.json","events_json":"https://pith.science/api/pith-number/A5XBTMKRABGDDAKGZQCTLJ2NDX/events.json","paper":"https://pith.science/paper/A5XBTMKR"},"agent_actions":{"view_html":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX","download_json":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX.json","view_paper":"https://pith.science/paper/A5XBTMKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07891&json=true","fetch_graph":"https://pith.science/api/pith-number/A5XBTMKRABGDDAKGZQCTLJ2NDX/graph.json","fetch_events":"https://pith.science/api/pith-number/A5XBTMKRABGDDAKGZQCTLJ2NDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX/action/storage_attestation","attest_author":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX/action/author_attestation","sign_citation":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX/action/citation_signature","submit_replication":"https://pith.science/pith/A5XBTMKRABGDDAKGZQCTLJ2NDX/action/replication_record"}},"created_at":"2026-07-05T02:08:22.944135+00:00","updated_at":"2026-07-05T02:08:22.944135+00:00"}