{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5YY3KTT5HS3H72ZZK5OXUPGYK6","short_pith_number":"pith:5YY3KTT5","canonical_record":{"source":{"id":"2305.02865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T14:22:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a7b42f37b72441f8212ce27421b2bfa5815faa9d862c018b52f88e9b8fee5ee","abstract_canon_sha256":"7fe4d898bec902121a97ddd4f380abf9d6d0c1011ca0acf5d6b42ebd519ea580"},"schema_version":"1.0"},"canonical_sha256":"ee31b54e7d3cb67feb39575d7a3cd857896712bcd2d118fc49120c5bc17eb5a5","source":{"kind":"arxiv","id":"2305.02865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02865","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02865v1","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02865","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"5YY3KTT5HS3H","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"5YY3KTT5HS3H72ZZ","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"5YY3KTT5","created_at":"2026-07-05T06:07:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5YY3KTT5HS3H72ZZK5OXUPGYK6","target":"record","payload":{"canonical_record":{"source":{"id":"2305.02865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T14:22:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a7b42f37b72441f8212ce27421b2bfa5815faa9d862c018b52f88e9b8fee5ee","abstract_canon_sha256":"7fe4d898bec902121a97ddd4f380abf9d6d0c1011ca0acf5d6b42ebd519ea580"},"schema_version":"1.0"},"canonical_sha256":"ee31b54e7d3cb67feb39575d7a3cd857896712bcd2d118fc49120c5bc17eb5a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:05.871061Z","signature_b64":"GNOX1E00Rtx7J2Bb0IKU7JOyjOgYl1kWxvLrrgM6wCNkBSrc5h4qQzibTNCiDtoylGfBMyq8YQVToLDhU0AQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee31b54e7d3cb67feb39575d7a3cd857896712bcd2d118fc49120c5bc17eb5a5","last_reissued_at":"2026-07-05T06:07:05.870516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:05.870516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.02865","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gat/Bix2M4lyzFIN/fm7G3oGN8cuAlwl7jKEE9c0daWBfVDSrsxfTUCwN+yHN7m2zMOgkF8eahEIFUqXZTH8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:00:47.016061Z"},"content_sha256":"eab1e6ab32b5f206374cdef3f4aee4d8906cd4842289e1cb09b5aaf24fdfeabd","schema_version":"1.0","event_id":"sha256:eab1e6ab32b5f206374cdef3f4aee4d8906cd4842289e1cb09b5aaf24fdfeabd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5YY3KTT5HS3H72ZZK5OXUPGYK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junjie Shan, Qi Zhang, Shihan Dou, Songyang Gao, Xuanjing Huang","submitted_at":"2023-05-04T14:22:26Z","abstract_excerpt":"Dataset bias, i.e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models. Existing works focus on eliminating dataset bias by down-weighting problematic data in the training process, which induce the omission of valid feature information while mitigating bias. In this work, We analyze the causes of dataset bias from the perspective of causal inference and propose CausalAPM, a generalizable literal disentangling framework to ameliorate the bias problem from feature granularity. The propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02865","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/2305.02865/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":"2026-07-05T06:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4dAuwZzDTpS+roDvwwPfbbMxOkTqWZSigcpADUzlqtPgvsJLswXXu/bMXT6WEs3HM6HUcC4YQcWQ1cAD5NYuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:00:47.016555Z"},"content_sha256":"bc4b025b38c1b36ef0349f285bdfa25b53b16cf5a6850b2e8b8d7147c6e9c6d1","schema_version":"1.0","event_id":"sha256:bc4b025b38c1b36ef0349f285bdfa25b53b16cf5a6850b2e8b8d7147c6e9c6d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/bundle.json","state_url":"https://pith.science/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/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":"2026-08-15T20:00:47Z","links":{"resolver":"https://pith.science/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6","bundle":"https://pith.science/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/bundle.json","state":"https://pith.science/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YY3KTT5HS3H72ZZK5OXUPGYK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5YY3KTT5HS3H72ZZK5OXUPGYK6","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":"7fe4d898bec902121a97ddd4f380abf9d6d0c1011ca0acf5d6b42ebd519ea580","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T14:22:26Z","title_canon_sha256":"1a7b42f37b72441f8212ce27421b2bfa5815faa9d862c018b52f88e9b8fee5ee"},"schema_version":"1.0","source":{"id":"2305.02865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02865","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02865v1","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02865","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"5YY3KTT5HS3H","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"5YY3KTT5HS3H72ZZ","created_at":"2026-07-05T06:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"5YY3KTT5","created_at":"2026-07-05T06:07:05Z"}],"graph_snapshots":[{"event_id":"sha256:bc4b025b38c1b36ef0349f285bdfa25b53b16cf5a6850b2e8b8d7147c6e9c6d1","target":"graph","created_at":"2026-07-05T06:07:05Z","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/2305.02865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataset bias, i.e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models. Existing works focus on eliminating dataset bias by down-weighting problematic data in the training process, which induce the omission of valid feature information while mitigating bias. In this work, We analyze the causes of dataset bias from the perspective of causal inference and propose CausalAPM, a generalizable literal disentangling framework to ameliorate the bias problem from feature granularity. The propos","authors_text":"Junjie Shan, Qi Zhang, Shihan Dou, Songyang Gao, Xuanjing Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T14:22:26Z","title":"CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02865","kind":"arxiv","version":1},"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:eab1e6ab32b5f206374cdef3f4aee4d8906cd4842289e1cb09b5aaf24fdfeabd","target":"record","created_at":"2026-07-05T06:07:05Z","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":"7fe4d898bec902121a97ddd4f380abf9d6d0c1011ca0acf5d6b42ebd519ea580","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T14:22:26Z","title_canon_sha256":"1a7b42f37b72441f8212ce27421b2bfa5815faa9d862c018b52f88e9b8fee5ee"},"schema_version":"1.0","source":{"id":"2305.02865","kind":"arxiv","version":1}},"canonical_sha256":"ee31b54e7d3cb67feb39575d7a3cd857896712bcd2d118fc49120c5bc17eb5a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee31b54e7d3cb67feb39575d7a3cd857896712bcd2d118fc49120c5bc17eb5a5","first_computed_at":"2026-07-05T06:07:05.870516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:05.870516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNOX1E00Rtx7J2Bb0IKU7JOyjOgYl1kWxvLrrgM6wCNkBSrc5h4qQzibTNCiDtoylGfBMyq8YQVToLDhU0AQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:05.871061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eab1e6ab32b5f206374cdef3f4aee4d8906cd4842289e1cb09b5aaf24fdfeabd","sha256:bc4b025b38c1b36ef0349f285bdfa25b53b16cf5a6850b2e8b8d7147c6e9c6d1"],"state_sha256":"bbca5e06c0cdda635816374a6599cdd8778ba9b870c8bc6c17ab578e136c6291"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wBHEAxqPyGGI8x7RDmWwqwlcmQlkHSPwVYfxbOedRsDthOdbH/LnAUX8vixx1DBrK4RKjelLbGJs5G8ISvjFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:00:47.020128Z","bundle_sha256":"0102d3b71285a8577756c039d9fef75df62cc59a954ac0e37991536276de5550"}}