{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z6NYS2S3H7ZFKOT35K5RBK4UGP","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":"413925cf896033ce20a2c6644e49ab378917f00f2e61e3d676520a8166aaa9d8","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-06T07:59:22Z","title_canon_sha256":"d6650d9096bc7e781ae9ba5b5904668054fe82743a7bea066f3390c324201342"},"schema_version":"1.0","source":{"id":"2012.03208","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.03208","created_at":"2026-07-05T03:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2012.03208v3","created_at":"2026-07-05T03:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03208","created_at":"2026-07-05T03:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z6NYS2S3H7ZF","created_at":"2026-07-05T03:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z6NYS2S3H7ZFKOT3","created_at":"2026-07-05T03:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z6NYS2S3","created_at":"2026-07-05T03:10:51Z"}],"graph_snapshots":[{"event_id":"sha256:60dc816057c4ab6c051dda6b846c2ffce5b18a75b8234eeb70b6ce18c0843d2d","target":"graph","created_at":"2026-07-05T03:10:51Z","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/2012.03208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for AI agents. The 'interactive instruction following' task attempts to make progress towards building agents that jointly navigate, interact, and reason in the environment at every step. To address the multifaceted problem, we propose a model that factorizes the task into interactive perception and action policy streams with enhanced components and name it as MOCA, a Modular Object-Centric Approach. We empirically validate that MOCA outperforms prior arts by significant m","authors_text":"Byeonghwi Kim, Jonghyun Choi, Kunal Pratap Singh, Roozbeh Mottaghi, Suvaansh Bhambri","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-06T07:59:22Z","title":"Factorizing Perception and Policy for Interactive Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03208","kind":"arxiv","version":3},"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":"sha256:050abc70934bd4fe5e33c0d29def6661f03e368cbe6ac2f173fc361d593613ea","target":"record","created_at":"2026-07-05T03:10:51Z","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":"413925cf896033ce20a2c6644e49ab378917f00f2e61e3d676520a8166aaa9d8","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-12-06T07:59:22Z","title_canon_sha256":"d6650d9096bc7e781ae9ba5b5904668054fe82743a7bea066f3390c324201342"},"schema_version":"1.0","source":{"id":"2012.03208","kind":"arxiv","version":3}},"canonical_sha256":"cf9b896a5b3ff2553a7beabb10ab9433f22f2ffb4caec10fa021f475018574e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf9b896a5b3ff2553a7beabb10ab9433f22f2ffb4caec10fa021f475018574e5","first_computed_at":"2026-07-05T03:10:51.258192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:10:51.258192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9jHOLQhzWdnjM8cwDSUty4K4MBEVcXHYfuXqQPVN+eLxjvWEYoiUHa4B/Bjg0levRQjK6yESN7ykvdPdqK8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:10:51.258745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.03208","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:050abc70934bd4fe5e33c0d29def6661f03e368cbe6ac2f173fc361d593613ea","sha256:60dc816057c4ab6c051dda6b846c2ffce5b18a75b8234eeb70b6ce18c0843d2d"],"state_sha256":"dfcc07c96878ef587fc022e618a7fedb097a875ee67864ecbf5e782ab5e43b97"}