{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:THILJ4LCGCKAJ5VQIT673SMGM6","short_pith_number":"pith:THILJ4LC","canonical_record":{"source":{"id":"2302.08635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T00:30:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5d176d7adabe3f4a25f58c9b4d8c75137686e6969dfd455546dd96ce009834ce","abstract_canon_sha256":"5977b1eff15ee6e43b6c567ea06931b953bedaec7e075bcae0286181fa6f734a"},"schema_version":"1.0"},"canonical_sha256":"99d0b4f162309404f6b044fdfdc9866787dc37b58d4e6e6805033416ff66fccd","source":{"kind":"arxiv","id":"2302.08635","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08635","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08635v2","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08635","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"THILJ4LCGCKA","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"THILJ4LCGCKAJ5VQ","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"THILJ4LC","created_at":"2026-07-05T06:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:THILJ4LCGCKAJ5VQIT673SMGM6","target":"record","payload":{"canonical_record":{"source":{"id":"2302.08635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T00:30:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5d176d7adabe3f4a25f58c9b4d8c75137686e6969dfd455546dd96ce009834ce","abstract_canon_sha256":"5977b1eff15ee6e43b6c567ea06931b953bedaec7e075bcae0286181fa6f734a"},"schema_version":"1.0"},"canonical_sha256":"99d0b4f162309404f6b044fdfdc9866787dc37b58d4e6e6805033416ff66fccd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:37.165979Z","signature_b64":"ZbvYcoijalRf0jSZz0WU+eV/sEHUheWumEkDXW8JkGAbTP061b+AgB9FkvrqW2ceR9jnJ9nP7ELEWGvNLNqZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d0b4f162309404f6b044fdfdc9866787dc37b58d4e6e6805033416ff66fccd","last_reissued_at":"2026-07-05T06:04:37.165562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:37.165562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.08635","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GF7ec4LY1J7KnxmRcgijm6nXUAhPWAJjE0KFrvV9gt+pxv0hd2CPCaMZ+HhwYziBGopUWz3NFfrpeg5BN44qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:49:37.371947Z"},"content_sha256":"092c55bc62401110ad88c7adb77d4d8b292da78e3559b27e163714a8be61cccf","schema_version":"1.0","event_id":"sha256:092c55bc62401110ad88c7adb77d4d8b292da78e3559b27e163714a8be61cccf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:THILJ4LCGCKAJ5VQIT673SMGM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark Crowley, Oliver Schulte, Shayan Shirahmad Gale Bagi, Zahra Gharaee","submitted_at":"2023-02-17T00:30:44Z","abstract_excerpt":"Conventional supervised learning methods typically assume i.i.d samples and are found to be sensitive to out-of-distribution (OOD) data. We propose Generative Causal Representation Learning (GCRL) which leverages causality to facilitate knowledge transfer under distribution shifts. While we evaluate the effectiveness of our proposed method in human trajectory prediction models, GCRL can be applied to other domains as well. First, we propose a novel causal model that explains the generative factors in motion forecasting datasets using features that are common across all environments and with fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08635","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/2302.08635/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2a0XohszHkpb73tsT3KgeqD6CbsS49LdLwQQLw8MRIq5tD7MM7PjEZ7XUhL1URubgp0aUvENQIgamnbEcbLwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:49:37.372329Z"},"content_sha256":"04dc1abb88a8e15a4ef1b64d3b3b0e19782bcdb8388e36955f28c45fb6d5fa91","schema_version":"1.0","event_id":"sha256:04dc1abb88a8e15a4ef1b64d3b3b0e19782bcdb8388e36955f28c45fb6d5fa91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THILJ4LCGCKAJ5VQIT673SMGM6/bundle.json","state_url":"https://pith.science/pith/THILJ4LCGCKAJ5VQIT673SMGM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THILJ4LCGCKAJ5VQIT673SMGM6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T04:49:37Z","links":{"resolver":"https://pith.science/pith/THILJ4LCGCKAJ5VQIT673SMGM6","bundle":"https://pith.science/pith/THILJ4LCGCKAJ5VQIT673SMGM6/bundle.json","state":"https://pith.science/pith/THILJ4LCGCKAJ5VQIT673SMGM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THILJ4LCGCKAJ5VQIT673SMGM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:THILJ4LCGCKAJ5VQIT673SMGM6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5977b1eff15ee6e43b6c567ea06931b953bedaec7e075bcae0286181fa6f734a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T00:30:44Z","title_canon_sha256":"5d176d7adabe3f4a25f58c9b4d8c75137686e6969dfd455546dd96ce009834ce"},"schema_version":"1.0","source":{"id":"2302.08635","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08635","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08635v2","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08635","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"THILJ4LCGCKA","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"THILJ4LCGCKAJ5VQ","created_at":"2026-07-05T06:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"THILJ4LC","created_at":"2026-07-05T06:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:04dc1abb88a8e15a4ef1b64d3b3b0e19782bcdb8388e36955f28c45fb6d5fa91","target":"graph","created_at":"2026-07-05T06:04:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.08635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional supervised learning methods typically assume i.i.d samples and are found to be sensitive to out-of-distribution (OOD) data. We propose Generative Causal Representation Learning (GCRL) which leverages causality to facilitate knowledge transfer under distribution shifts. While we evaluate the effectiveness of our proposed method in human trajectory prediction models, GCRL can be applied to other domains as well. First, we propose a novel causal model that explains the generative factors in motion forecasting datasets using features that are common across all environments and with fe","authors_text":"Mark Crowley, Oliver Schulte, Shayan Shirahmad Gale Bagi, Zahra Gharaee","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T00:30:44Z","title":"Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08635","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:092c55bc62401110ad88c7adb77d4d8b292da78e3559b27e163714a8be61cccf","target":"record","created_at":"2026-07-05T06:04:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5977b1eff15ee6e43b6c567ea06931b953bedaec7e075bcae0286181fa6f734a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T00:30:44Z","title_canon_sha256":"5d176d7adabe3f4a25f58c9b4d8c75137686e6969dfd455546dd96ce009834ce"},"schema_version":"1.0","source":{"id":"2302.08635","kind":"arxiv","version":2}},"canonical_sha256":"99d0b4f162309404f6b044fdfdc9866787dc37b58d4e6e6805033416ff66fccd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99d0b4f162309404f6b044fdfdc9866787dc37b58d4e6e6805033416ff66fccd","first_computed_at":"2026-07-05T06:04:37.165562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:37.165562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZbvYcoijalRf0jSZz0WU+eV/sEHUheWumEkDXW8JkGAbTP061b+AgB9FkvrqW2ceR9jnJ9nP7ELEWGvNLNqZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:37.165979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08635","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:092c55bc62401110ad88c7adb77d4d8b292da78e3559b27e163714a8be61cccf","sha256:04dc1abb88a8e15a4ef1b64d3b3b0e19782bcdb8388e36955f28c45fb6d5fa91"],"state_sha256":"3a560f7e3e0c0ff4532d1e82d3eed99c7f44c933b3673dd2f962b16e4a8d369c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ic6Fd8BaeY4XBLbIYTUB9vEnq60BSvoSWLG4r2oZ6UlHPNntfPJyKJn25qC4x98pt5kNUy0JrniWP9IatNlaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:49:37.374322Z","bundle_sha256":"ac4d387c5889d672fcdfd98a9e5a378248e5ac1e3b2920be897c54608687a241"}}