{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7MNSCB5E6TLWHKSRQPZSNHMIMY","short_pith_number":"pith:7MNSCB5E","schema_version":"1.0","canonical_sha256":"fb1b2107a4f4d763aa5183f3269d88660bc25fc9288815ebaf72200362de49a5","source":{"kind":"arxiv","id":"2005.04625","version":2},"attestation_state":"computed","paper":{"title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Eugene Ie, Fei Sha, Hexiang Hu, Jiacheng Chen, Vihan Jain, Wang Zhu, Zhiwei Deng","submitted_at":"2020-05-10T10:46:41Z","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"},"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":"2005.04625","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-05-10T10:46:41Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c9dd5558597fa4969151a35c235aa7f4827551f143160d98e475e4bf75a5c111","abstract_canon_sha256":"bce38eeb9c0788728f7be89d15622764501e4c805618ffefe4ddb26fa2a20471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:15.551855Z","signature_b64":"brJOpzsUwgM6uH7GQHzfOOpJOOHXNFK8MIV3wlrc5yDoI+VJ8Plg5ms5RCM18CKRS0Rmntii+qCC932VwiGwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb1b2107a4f4d763aa5183f3269d88660bc25fc9288815ebaf72200362de49a5","last_reissued_at":"2026-07-05T01:10:15.551353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:15.551353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Eugene Ie, Fei Sha, Hexiang Hu, Jiacheng Chen, Vihan Jain, Wang Zhu, Zhiwei Deng","submitted_at":"2020-05-10T10:46:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04625","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/2005.04625/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":"2005.04625","created_at":"2026-07-05T01:10:15.551412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04625v2","created_at":"2026-07-05T01:10:15.551412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04625","created_at":"2026-07-05T01:10:15.551412+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MNSCB5E6TLW","created_at":"2026-07-05T01:10:15.551412+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MNSCB5E6TLWHKSR","created_at":"2026-07-05T01:10:15.551412+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MNSCB5E","created_at":"2026-07-05T01:10:15.551412+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/7MNSCB5E6TLWHKSRQPZSNHMIMY","json":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY.json","graph_json":"https://pith.science/api/pith-number/7MNSCB5E6TLWHKSRQPZSNHMIMY/graph.json","events_json":"https://pith.science/api/pith-number/7MNSCB5E6TLWHKSRQPZSNHMIMY/events.json","paper":"https://pith.science/paper/7MNSCB5E"},"agent_actions":{"view_html":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY","download_json":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY.json","view_paper":"https://pith.science/paper/7MNSCB5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04625&json=true","fetch_graph":"https://pith.science/api/pith-number/7MNSCB5E6TLWHKSRQPZSNHMIMY/graph.json","fetch_events":"https://pith.science/api/pith-number/7MNSCB5E6TLWHKSRQPZSNHMIMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY/action/storage_attestation","attest_author":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY/action/author_attestation","sign_citation":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY/action/citation_signature","submit_replication":"https://pith.science/pith/7MNSCB5E6TLWHKSRQPZSNHMIMY/action/replication_record"}},"created_at":"2026-07-05T01:10:15.551412+00:00","updated_at":"2026-07-05T01:10:15.551412+00:00"}