{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NEV4OI6F26VE4245M473P2SMX4","short_pith_number":"pith:NEV4OI6F","schema_version":"1.0","canonical_sha256":"692bc723c5d7aa4e6b9d673fb7ea4cbf122a8e2050804c49cc8eac755ac2f00b","source":{"kind":"arxiv","id":"2403.07548","version":2},"attestation_state":"computed","paper":{"title":"Online Continual Learning For Interactive Instruction Following Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Byeonghwi Kim, Jonghyun Choi, Minhyuk Seo","submitted_at":"2024-03-12T11:33:48Z","abstract_excerpt":"In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic agent is supposed to learn the world continuously as it explores and perceives it. To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremental Learning, Behavior-IL) and new environments (Environment Incremental Learning, Environment-IL) Fo"},"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":"2403.07548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-12T11:33:48Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"93fefbfca1c3b6a17ebb1500a4e3a5e384d297265149efb917fd2e9299f47740","abstract_canon_sha256":"9d1e182ecf453393ec79d589fef96694949c917fac20eb2036712f76b71a5926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:31.012273Z","signature_b64":"Rf4SyN18iCi4JNUNwMsSI24Nf75en/iNpdtojBJAoVhb/BAFlGlPraITWfKaHUJuUU4tYp8YZrZizvT4BB7HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692bc723c5d7aa4e6b9d673fb7ea4cbf122a8e2050804c49cc8eac755ac2f00b","last_reissued_at":"2026-07-05T07:55:31.011880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:31.011880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Continual Learning For Interactive Instruction Following Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Byeonghwi Kim, Jonghyun Choi, Minhyuk Seo","submitted_at":"2024-03-12T11:33:48Z","abstract_excerpt":"In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic agent is supposed to learn the world continuously as it explores and perceives it. To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremental Learning, Behavior-IL) and new environments (Environment Incremental Learning, Environment-IL) Fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07548","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/2403.07548/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":"2403.07548","created_at":"2026-07-05T07:55:31.011935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07548v2","created_at":"2026-07-05T07:55:31.011935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07548","created_at":"2026-07-05T07:55:31.011935+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEV4OI6F26VE","created_at":"2026-07-05T07:55:31.011935+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEV4OI6F26VE4245","created_at":"2026-07-05T07:55:31.011935+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEV4OI6F","created_at":"2026-07-05T07:55:31.011935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12305","citing_title":"PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4","json":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4.json","graph_json":"https://pith.science/api/pith-number/NEV4OI6F26VE4245M473P2SMX4/graph.json","events_json":"https://pith.science/api/pith-number/NEV4OI6F26VE4245M473P2SMX4/events.json","paper":"https://pith.science/paper/NEV4OI6F"},"agent_actions":{"view_html":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4","download_json":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4.json","view_paper":"https://pith.science/paper/NEV4OI6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07548&json=true","fetch_graph":"https://pith.science/api/pith-number/NEV4OI6F26VE4245M473P2SMX4/graph.json","fetch_events":"https://pith.science/api/pith-number/NEV4OI6F26VE4245M473P2SMX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4/action/storage_attestation","attest_author":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4/action/author_attestation","sign_citation":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4/action/citation_signature","submit_replication":"https://pith.science/pith/NEV4OI6F26VE4245M473P2SMX4/action/replication_record"}},"created_at":"2026-07-05T07:55:31.011935+00:00","updated_at":"2026-07-05T07:55:31.011935+00:00"}