{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LMMHC3Y3CYARQEKXMWFU2RGA6W","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":"f3b8d5b02ebd1e065d6c467973294ac7d81c1fe4a820577e752d66ee550c49d0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T00:21:54Z","title_canon_sha256":"b67ab18070e5da9d75ed393f62fa1cf28ebc0e5442795a01cbf3a131b3461fdc"},"schema_version":"1.0","source":{"id":"2105.11589","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11589","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11589v2","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11589","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"LMMHC3Y3CYAR","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"LMMHC3Y3CYARQEKX","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"LMMHC3Y3","created_at":"2026-07-05T04:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:da25389570700d3be7d7f3be7e85cdc89708f19e34dff93c2f1b7a7cb2becd7f","target":"graph","created_at":"2026-07-05T04:05:31Z","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/2105.11589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ayush Shrivastava, Devi Parikh, Dilek Hakkani-T\\\"ur, Gokhan T\\\"ur, Karthik Gopalakrishnan, Robinson Piramuthu, Yang Liu","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T00:21:54Z","title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11589","kind":"arxiv","version":2},"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:b00419adc263233277064a730337cf33c29393519e566a758c27351669247ca4","target":"record","created_at":"2026-07-05T04:05:31Z","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":"f3b8d5b02ebd1e065d6c467973294ac7d81c1fe4a820577e752d66ee550c49d0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T00:21:54Z","title_canon_sha256":"b67ab18070e5da9d75ed393f62fa1cf28ebc0e5442795a01cbf3a131b3461fdc"},"schema_version":"1.0","source":{"id":"2105.11589","kind":"arxiv","version":2}},"canonical_sha256":"5b18716f1b1601181157658b4d44c0f58634703c8dfbe3455327abd425816023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b18716f1b1601181157658b4d44c0f58634703c8dfbe3455327abd425816023","first_computed_at":"2026-07-05T04:05:31.155664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:31.155664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ltr5Q0TEHtVfZtOxcsdLwi4BuEVXd3pJF+SN2Donc0W61AQY7dULeiwv1Z8QBOYIZRSXLnlRTp81tfHvLLOeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:31.156137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11589","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b00419adc263233277064a730337cf33c29393519e566a758c27351669247ca4","sha256:da25389570700d3be7d7f3be7e85cdc89708f19e34dff93c2f1b7a7cb2becd7f"],"state_sha256":"a68c3034b24dca470d56da950119ba8b17ee989891f462a2f9e8e3d45a383570"}