{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NRCY3UL7ZO63NE5DA5PBWO2MOO","short_pith_number":"pith:NRCY3UL7","schema_version":"1.0","canonical_sha256":"6c458dd17fcbbdb693a3075e1b3b4c73acfa0a0d753067b94e9fce62f58d5a1a","source":{"kind":"arxiv","id":"2310.12344","version":1},"attestation_state":"computed","paper":{"title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Cheng-Fu Yang, Jianwei Yang, Kai-Wei Chang, Lu Yuan, Xiyang Dai, Yen-Chun Chen, Yu-Chiang Frank Wang","submitted_at":"2023-10-18T21:43:07Z","abstract_excerpt":"End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent's insensitivity to subtle changes in natural language instructions. To mitigate this issue, we propose explicitly aligning the agent's hidden states with the instructions via contrastive learning. Nevertheless, the semantic gap between high-level language instructions and the agent's low-level action space remains an obstacle"},"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":"2310.12344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T21:43:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c18361650fc6e2ce97cbf0abd5d28623993204239fcf046d921fc47ea70935a","abstract_canon_sha256":"40386a11e9a535592b2c893834c6a49ccf7ac40c8a795478ad67ec9303445393"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:36.736898Z","signature_b64":"ou6mAVSHP/wwhIawk0t1IXF29g7UxNaXhZNGHCh780BhNXWl4fxQoOWTHD5XNshhhwARWH+eWEZH9HKGrJy3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c458dd17fcbbdb693a3075e1b3b4c73acfa0a0d753067b94e9fce62f58d5a1a","last_reissued_at":"2026-07-05T07:02:36.736374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:36.736374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Cheng-Fu Yang, Jianwei Yang, Kai-Wei Chang, Lu Yuan, Xiyang Dai, Yen-Chun Chen, Yu-Chiang Frank Wang","submitted_at":"2023-10-18T21:43:07Z","abstract_excerpt":"End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent's insensitivity to subtle changes in natural language instructions. To mitigate this issue, we propose explicitly aligning the agent's hidden states with the instructions via contrastive learning. Nevertheless, the semantic gap between high-level language instructions and the agent's low-level action space remains an obstacle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12344","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/2310.12344/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":"2310.12344","created_at":"2026-07-05T07:02:36.736443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12344v1","created_at":"2026-07-05T07:02:36.736443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12344","created_at":"2026-07-05T07:02:36.736443+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRCY3UL7ZO63","created_at":"2026-07-05T07:02:36.736443+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRCY3UL7ZO63NE5D","created_at":"2026-07-05T07:02:36.736443+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRCY3UL7","created_at":"2026-07-05T07:02:36.736443+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/NRCY3UL7ZO63NE5DA5PBWO2MOO","json":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO.json","graph_json":"https://pith.science/api/pith-number/NRCY3UL7ZO63NE5DA5PBWO2MOO/graph.json","events_json":"https://pith.science/api/pith-number/NRCY3UL7ZO63NE5DA5PBWO2MOO/events.json","paper":"https://pith.science/paper/NRCY3UL7"},"agent_actions":{"view_html":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO","download_json":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO.json","view_paper":"https://pith.science/paper/NRCY3UL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12344&json=true","fetch_graph":"https://pith.science/api/pith-number/NRCY3UL7ZO63NE5DA5PBWO2MOO/graph.json","fetch_events":"https://pith.science/api/pith-number/NRCY3UL7ZO63NE5DA5PBWO2MOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO/action/storage_attestation","attest_author":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO/action/author_attestation","sign_citation":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO/action/citation_signature","submit_replication":"https://pith.science/pith/NRCY3UL7ZO63NE5DA5PBWO2MOO/action/replication_record"}},"created_at":"2026-07-05T07:02:36.736443+00:00","updated_at":"2026-07-05T07:02:36.736443+00:00"}