{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:N6SZSDQZPSORDOCVUGRX6W4NBV","short_pith_number":"pith:N6SZSDQZ","canonical_record":{"source":{"id":"2108.02684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T15:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"2d4c5fb5ccf649abf63a12db7048c15554484cd7e0e3ec88e5aa6f1ce049741c","abstract_canon_sha256":"ea556a6fcbec0b9cd256df94d4319e993a35f7e975ecd173e99c223568e5970a"},"schema_version":"1.0"},"canonical_sha256":"6fa5990e197c9d11b855a1a37f5b8d0d77651d55c22e270541e1a4da3cbdd0ed","source":{"kind":"arxiv","id":"2108.02684","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02684","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02684v1","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02684","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"N6SZSDQZPSOR","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"N6SZSDQZPSORDOCV","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"N6SZSDQZ","created_at":"2026-07-05T03:03:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:N6SZSDQZPSORDOCVUGRX6W4NBV","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T15:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"2d4c5fb5ccf649abf63a12db7048c15554484cd7e0e3ec88e5aa6f1ce049741c","abstract_canon_sha256":"ea556a6fcbec0b9cd256df94d4319e993a35f7e975ecd173e99c223568e5970a"},"schema_version":"1.0"},"canonical_sha256":"6fa5990e197c9d11b855a1a37f5b8d0d77651d55c22e270541e1a4da3cbdd0ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:35.329180Z","signature_b64":"tzY8AuSqPhSQyy4hjxf38wHkNIo10XluB1eA/S0ZWW+NK7s/K/uLsiWHqiXL7Ios3jAyBsC0VGlDWpFI3dibAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa5990e197c9d11b855a1a37f5b8d0d77651d55c22e270541e1a4da3cbdd0ed","last_reissued_at":"2026-07-05T03:03:35.328694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:35.328694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02684","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":"2026-07-05T03:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STMvYTwcydvvSh+Sn0T61anu9FM23Lqf9qcj8yEkP4KWBAPkWE7nqeRFHXwsMEprgBX1aSH+jl2IMIVYm9T+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:44:46.546417Z"},"content_sha256":"892586b8276a2b0e6225846ac17bf45f6809045ee4d41809faf0624c57cdb1ef","schema_version":"1.0","event_id":"sha256:892586b8276a2b0e6225846ac17bf45f6809045ee4d41809faf0624c57cdb1ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:N6SZSDQZPSORDOCVUGRX6W4NBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Out-of-Distribution Generalization in Text Classifiers Trained on Tobacco-3482 and RVL-CDIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Navtej Singh, Saarthak Maheshwari, Shanti Stewart, Stefan Larson, Uma Krishnaswamy","submitted_at":"2021-08-05T15:34:56Z","abstract_excerpt":"To be robust enough for widespread adoption, document analysis systems involving machine learning models must be able to respond correctly to inputs that fall outside of the data distribution that was used to generate the data on which the models were trained. This paper explores the ability of text classifiers trained on standard document classification datasets to generalize to out-of-distribution documents at inference time. We take the Tobacco-3482 and RVL-CDIP datasets as a starting point and generate new out-of-distribution evaluation datasets in order to analyze the generalization perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02684","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/2108.02684/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":"2026-07-05T03:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kXh0c5UzGhDKaY1bC7fcN7rHO7iVZA9qy4dW4DwLhiQ9mAJc1vvLKYHrnQ6NAgZWaTkOTaFH425qC3wWy17jDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T00:44:46.546790Z"},"content_sha256":"9bc320528e1b4457655039bd8a66b94acc0914290291687ecc120ab4f7bcbb91","schema_version":"1.0","event_id":"sha256:9bc320528e1b4457655039bd8a66b94acc0914290291687ecc120ab4f7bcbb91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/bundle.json","state_url":"https://pith.science/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/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":"2026-07-26T00:44:46Z","links":{"resolver":"https://pith.science/pith/N6SZSDQZPSORDOCVUGRX6W4NBV","bundle":"https://pith.science/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/bundle.json","state":"https://pith.science/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6SZSDQZPSORDOCVUGRX6W4NBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N6SZSDQZPSORDOCVUGRX6W4NBV","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":"ea556a6fcbec0b9cd256df94d4319e993a35f7e975ecd173e99c223568e5970a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T15:34:56Z","title_canon_sha256":"2d4c5fb5ccf649abf63a12db7048c15554484cd7e0e3ec88e5aa6f1ce049741c"},"schema_version":"1.0","source":{"id":"2108.02684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02684","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02684v1","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02684","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"N6SZSDQZPSOR","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"N6SZSDQZPSORDOCV","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"N6SZSDQZ","created_at":"2026-07-05T03:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:9bc320528e1b4457655039bd8a66b94acc0914290291687ecc120ab4f7bcbb91","target":"graph","created_at":"2026-07-05T03:03:35Z","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/2108.02684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To be robust enough for widespread adoption, document analysis systems involving machine learning models must be able to respond correctly to inputs that fall outside of the data distribution that was used to generate the data on which the models were trained. This paper explores the ability of text classifiers trained on standard document classification datasets to generalize to out-of-distribution documents at inference time. We take the Tobacco-3482 and RVL-CDIP datasets as a starting point and generate new out-of-distribution evaluation datasets in order to analyze the generalization perfo","authors_text":"Navtej Singh, Saarthak Maheshwari, Shanti Stewart, Stefan Larson, Uma Krishnaswamy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T15:34:56Z","title":"Exploring Out-of-Distribution Generalization in Text Classifiers Trained on Tobacco-3482 and RVL-CDIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02684","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":"sha256:892586b8276a2b0e6225846ac17bf45f6809045ee4d41809faf0624c57cdb1ef","target":"record","created_at":"2026-07-05T03:03:35Z","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":"ea556a6fcbec0b9cd256df94d4319e993a35f7e975ecd173e99c223568e5970a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T15:34:56Z","title_canon_sha256":"2d4c5fb5ccf649abf63a12db7048c15554484cd7e0e3ec88e5aa6f1ce049741c"},"schema_version":"1.0","source":{"id":"2108.02684","kind":"arxiv","version":1}},"canonical_sha256":"6fa5990e197c9d11b855a1a37f5b8d0d77651d55c22e270541e1a4da3cbdd0ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fa5990e197c9d11b855a1a37f5b8d0d77651d55c22e270541e1a4da3cbdd0ed","first_computed_at":"2026-07-05T03:03:35.328694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:35.328694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tzY8AuSqPhSQyy4hjxf38wHkNIo10XluB1eA/S0ZWW+NK7s/K/uLsiWHqiXL7Ios3jAyBsC0VGlDWpFI3dibAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:35.329180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:892586b8276a2b0e6225846ac17bf45f6809045ee4d41809faf0624c57cdb1ef","sha256:9bc320528e1b4457655039bd8a66b94acc0914290291687ecc120ab4f7bcbb91"],"state_sha256":"0f53e8f46185fcbdf977b155dfc37e9a394c3a6f2b410cf75836e52ef0cbe3fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3ax7GEghF0Q7lk5I4euWLuna4u0jLUqi0GzW0kzFEB9+Woi2sfSbGH5x7C7vlmMGC9xBSpHimKRsT+h+SCEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T00:44:46.548923Z","bundle_sha256":"9cf2e849a34b5199c217e3df061866b9d8038ec4e5ec2a062ce1c0a0d6a1a61c"}}