{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7MNSCB5E6TLWHKSRQPZSNHMIMY","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":"bce38eeb9c0788728f7be89d15622764501e4c805618ffefe4ddb26fa2a20471","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-05-10T10:46:41Z","title_canon_sha256":"c9dd5558597fa4969151a35c235aa7f4827551f143160d98e475e4bf75a5c111"},"schema_version":"1.0","source":{"id":"2005.04625","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.04625","created_at":"2026-07-05T01:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2005.04625v2","created_at":"2026-07-05T01:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04625","created_at":"2026-07-05T01:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"7MNSCB5E6TLW","created_at":"2026-07-05T01:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"7MNSCB5E6TLWHKSR","created_at":"2026-07-05T01:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"7MNSCB5E","created_at":"2026-07-05T01:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:599a2610ca2c0ae70e5f2e0bc0805f167d16d50f366572ca62b651adaef69d77","target":"graph","created_at":"2026-07-05T01:10:15Z","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/2005.04625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN). In this paper, we study how an agent can navigate long paths when learning from a corpus that consists of shorter ones. We show that existing state-of-the-art agents do not generalize well. To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially. A special design memory buffer is used by the agent to turn its past experiences into contexts for future steps","authors_text":"Eugene Ie, Fei Sha, Hexiang Hu, Jiacheng Chen, Vihan Jain, Wang Zhu, Zhiwei Deng","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-05-10T10:46:41Z","title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04625","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":"sha256:6b774cb2852ac760ea076b94071f3554bbf855d044272bde36e17e79952cc1fa","target":"record","created_at":"2026-07-05T01:10:15Z","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":"bce38eeb9c0788728f7be89d15622764501e4c805618ffefe4ddb26fa2a20471","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-05-10T10:46:41Z","title_canon_sha256":"c9dd5558597fa4969151a35c235aa7f4827551f143160d98e475e4bf75a5c111"},"schema_version":"1.0","source":{"id":"2005.04625","kind":"arxiv","version":2}},"canonical_sha256":"fb1b2107a4f4d763aa5183f3269d88660bc25fc9288815ebaf72200362de49a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb1b2107a4f4d763aa5183f3269d88660bc25fc9288815ebaf72200362de49a5","first_computed_at":"2026-07-05T01:10:15.551353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:15.551353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"brJOpzsUwgM6uH7GQHzfOOpJOOHXNFK8MIV3wlrc5yDoI+VJ8Plg5ms5RCM18CKRS0Rmntii+qCC932VwiGwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:15.551855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.04625","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b774cb2852ac760ea076b94071f3554bbf855d044272bde36e17e79952cc1fa","sha256:599a2610ca2c0ae70e5f2e0bc0805f167d16d50f366572ca62b651adaef69d77"],"state_sha256":"51f5e76f867efcb0abe86660cc9f713be5901a336a09ad3ce963b1484d505403"}