{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LMMHC3Y3CYARQEKXMWFU2RGA6W","short_pith_number":"pith:LMMHC3Y3","schema_version":"1.0","canonical_sha256":"5b18716f1b1601181157658b4d44c0f58634703c8dfbe3455327abd425816023","source":{"kind":"arxiv","id":"2105.11589","version":2},"attestation_state":"computed","paper":{"title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator","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":"Ayush Shrivastava, Devi Parikh, Dilek Hakkani-T\\\"ur, Gokhan T\\\"ur, Karthik Gopalakrishnan, Robinson Piramuthu, Yang Liu","submitted_at":"2021-05-25T00:21:54Z","abstract_excerpt":"Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON is trained to: i) identify and associate object-level concepts and semantics between the environment and dialogue history, ii) identify when to interact vs. navigate via imitation learning "},"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":"2105.11589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T00:21:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"b67ab18070e5da9d75ed393f62fa1cf28ebc0e5442795a01cbf3a131b3461fdc","abstract_canon_sha256":"f3b8d5b02ebd1e065d6c467973294ac7d81c1fe4a820577e752d66ee550c49d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:31.156137Z","signature_b64":"ltr5Q0TEHtVfZtOxcsdLwi4BuEVXd3pJF+SN2Donc0W61AQY7dULeiwv1Z8QBOYIZRSXLnlRTp81tfHvLLOeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b18716f1b1601181157658b4d44c0f58634703c8dfbe3455327abd425816023","last_reissued_at":"2026-07-05T04:05:31.155664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:31.155664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator","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":"Ayush Shrivastava, Devi Parikh, Dilek Hakkani-T\\\"ur, Gokhan T\\\"ur, Karthik Gopalakrishnan, Robinson Piramuthu, Yang Liu","submitted_at":"2021-05-25T00:21:54Z","abstract_excerpt":"Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON is trained to: i) identify and associate object-level concepts and semantics between the environment and dialogue history, ii) identify when to interact vs. navigate via imitation learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11589","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/2105.11589/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":"2105.11589","created_at":"2026-07-05T04:05:31.155733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11589v2","created_at":"2026-07-05T04:05:31.155733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11589","created_at":"2026-07-05T04:05:31.155733+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMMHC3Y3CYAR","created_at":"2026-07-05T04:05:31.155733+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMMHC3Y3CYARQEKX","created_at":"2026-07-05T04:05:31.155733+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMMHC3Y3","created_at":"2026-07-05T04:05:31.155733+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/LMMHC3Y3CYARQEKXMWFU2RGA6W","json":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W.json","graph_json":"https://pith.science/api/pith-number/LMMHC3Y3CYARQEKXMWFU2RGA6W/graph.json","events_json":"https://pith.science/api/pith-number/LMMHC3Y3CYARQEKXMWFU2RGA6W/events.json","paper":"https://pith.science/paper/LMMHC3Y3"},"agent_actions":{"view_html":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W","download_json":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W.json","view_paper":"https://pith.science/paper/LMMHC3Y3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11589&json=true","fetch_graph":"https://pith.science/api/pith-number/LMMHC3Y3CYARQEKXMWFU2RGA6W/graph.json","fetch_events":"https://pith.science/api/pith-number/LMMHC3Y3CYARQEKXMWFU2RGA6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W/action/storage_attestation","attest_author":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W/action/author_attestation","sign_citation":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W/action/citation_signature","submit_replication":"https://pith.science/pith/LMMHC3Y3CYARQEKXMWFU2RGA6W/action/replication_record"}},"created_at":"2026-07-05T04:05:31.155733+00:00","updated_at":"2026-07-05T04:05:31.155733+00:00"}