{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P5QFSRCOEAX5A6PAOVVTNHKPAI","short_pith_number":"pith:P5QFSRCO","schema_version":"1.0","canonical_sha256":"7f6059444e202fd079e0756b369d4f0233e3fafa81d3cb00716dc5cdaa03a723","source":{"kind":"arxiv","id":"2405.18917","version":2},"attestation_state":"computed","paper":{"title":"Causal Action Influence Aware Counterfactual Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Georg Martius, Marco Bagatella, Marin Vlastelica, N\\'uria Armengol Urp\\'i","submitted_at":"2024-05-29T09:19:50Z","abstract_excerpt":"Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online enviro"},"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":"2405.18917","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T09:19:50Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"63f2283ba720167e676ecdd37f456b2f0bc98386fd8f950cfc12fdeaea8284f9","abstract_canon_sha256":"795795326027832280e7d79752309d87c036f310051e9dd7ea10deed4f6c000e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:13.662443Z","signature_b64":"YLOYF3iVUsPEYxqw5tKhc2NKkGeHxPSQKcbIUhRZ0eDghAisi52u++7W2R8CT1L5bjQk6rs4/kuv5/fDhuMeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f6059444e202fd079e0756b369d4f0233e3fafa81d3cb00716dc5cdaa03a723","last_reissued_at":"2026-07-05T09:48:13.662000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:13.662000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Action Influence Aware Counterfactual Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Georg Martius, Marco Bagatella, Marin Vlastelica, N\\'uria Armengol Urp\\'i","submitted_at":"2024-05-29T09:19:50Z","abstract_excerpt":"Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online enviro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18917","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/2405.18917/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":"2405.18917","created_at":"2026-07-05T09:48:13.662059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18917v2","created_at":"2026-07-05T09:48:13.662059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18917","created_at":"2026-07-05T09:48:13.662059+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5QFSRCOEAX5","created_at":"2026-07-05T09:48:13.662059+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5QFSRCOEAX5A6PA","created_at":"2026-07-05T09:48:13.662059+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5QFSRCO","created_at":"2026-07-05T09:48:13.662059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19580","citing_title":"PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13920","citing_title":"Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI","json":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI.json","graph_json":"https://pith.science/api/pith-number/P5QFSRCOEAX5A6PAOVVTNHKPAI/graph.json","events_json":"https://pith.science/api/pith-number/P5QFSRCOEAX5A6PAOVVTNHKPAI/events.json","paper":"https://pith.science/paper/P5QFSRCO"},"agent_actions":{"view_html":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI","download_json":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI.json","view_paper":"https://pith.science/paper/P5QFSRCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18917&json=true","fetch_graph":"https://pith.science/api/pith-number/P5QFSRCOEAX5A6PAOVVTNHKPAI/graph.json","fetch_events":"https://pith.science/api/pith-number/P5QFSRCOEAX5A6PAOVVTNHKPAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI/action/storage_attestation","attest_author":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI/action/author_attestation","sign_citation":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI/action/citation_signature","submit_replication":"https://pith.science/pith/P5QFSRCOEAX5A6PAOVVTNHKPAI/action/replication_record"}},"created_at":"2026-07-05T09:48:13.662059+00:00","updated_at":"2026-07-05T09:48:13.662059+00:00"}