{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VGDLLL2DPLKLX3G7N2J44KS2GR","short_pith_number":"pith:VGDLLL2D","schema_version":"1.0","canonical_sha256":"a986b5af437ad4bbecdf6e93ce2a5a347f5707806f05a79ea922c8839c3d7847","source":{"kind":"arxiv","id":"2111.07228","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Learning for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiajie Peng, Jianqing Fan, Jiwen Zhang, Zhongyu Wei","submitted_at":"2021-11-14T03:02:07Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments "},"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":"2111.07228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-14T03:02:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"560f910d78d84e8e0e2db8cfdd127aa06f899dfb08e40c2bef4e11dbaeb7a8e7","abstract_canon_sha256":"483d967c882c68212271abeba4b79b928887f48d9948ee48cb8a8b3a8aaa63a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:37.682739Z","signature_b64":"L5Ak3v6vMWqBKocCvOqIQ+s6XamJonizC2NiuLeV7FbGz7d4I5dC3CUq1ddr6JIvKoRiSuhLCRpyuYaDnXHDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a986b5af437ad4bbecdf6e93ce2a5a347f5707806f05a79ea922c8839c3d7847","last_reissued_at":"2026-07-05T03:31:37.682394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:37.682394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Learning for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiajie Peng, Jianqing Fan, Jiwen Zhang, Zhongyu Wei","submitted_at":"2021-11-14T03:02:07Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07228","kind":"arxiv","version":1},"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/2111.07228/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":"2111.07228","created_at":"2026-07-05T03:31:37.682454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.07228v1","created_at":"2026-07-05T03:31:37.682454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07228","created_at":"2026-07-05T03:31:37.682454+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGDLLL2DPLKL","created_at":"2026-07-05T03:31:37.682454+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGDLLL2DPLKLX3G7","created_at":"2026-07-05T03:31:37.682454+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGDLLL2D","created_at":"2026-07-05T03:31:37.682454+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/VGDLLL2DPLKLX3G7N2J44KS2GR","json":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR.json","graph_json":"https://pith.science/api/pith-number/VGDLLL2DPLKLX3G7N2J44KS2GR/graph.json","events_json":"https://pith.science/api/pith-number/VGDLLL2DPLKLX3G7N2J44KS2GR/events.json","paper":"https://pith.science/paper/VGDLLL2D"},"agent_actions":{"view_html":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR","download_json":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR.json","view_paper":"https://pith.science/paper/VGDLLL2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.07228&json=true","fetch_graph":"https://pith.science/api/pith-number/VGDLLL2DPLKLX3G7N2J44KS2GR/graph.json","fetch_events":"https://pith.science/api/pith-number/VGDLLL2DPLKLX3G7N2J44KS2GR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR/action/storage_attestation","attest_author":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR/action/author_attestation","sign_citation":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR/action/citation_signature","submit_replication":"https://pith.science/pith/VGDLLL2DPLKLX3G7N2J44KS2GR/action/replication_record"}},"created_at":"2026-07-05T03:31:37.682454+00:00","updated_at":"2026-07-05T03:31:37.682454+00:00"}