{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YQEXNNADVOYF2CRDUAQBRKG7UJ","short_pith_number":"pith:YQEXNNAD","canonical_record":{"source":{"id":"2203.08445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"3f0c65e9c22076e314895bc355cadbf8d611a119361bb944ec4377699f29b540","abstract_canon_sha256":"b6de79cc5fee76e395028b96772395b577c33e52101bada93cca5830ce1bff75"},"schema_version":"1.0"},"canonical_sha256":"c40976b403abb05d0a23a02018a8dfa242b94e437d569251310f14cca2f9f61c","source":{"kind":"arxiv","id":"2203.08445","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08445","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08445v2","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08445","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"YQEXNNADVOYF","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"YQEXNNADVOYF2CRD","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"YQEXNNAD","created_at":"2026-07-05T05:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YQEXNNADVOYF2CRDUAQBRKG7UJ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.08445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"3f0c65e9c22076e314895bc355cadbf8d611a119361bb944ec4377699f29b540","abstract_canon_sha256":"b6de79cc5fee76e395028b96772395b577c33e52101bada93cca5830ce1bff75"},"schema_version":"1.0"},"canonical_sha256":"c40976b403abb05d0a23a02018a8dfa242b94e437d569251310f14cca2f9f61c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:28.002020Z","signature_b64":"tsQbpp8Espd5X/fRkgJiTLSwI2vHaIhNomllMORT+JeUK61mqF55TCcGaXG/7G4aDKg0Rzz8csVZS/gDZOHqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40976b403abb05d0a23a02018a8dfa242b94e437d569251310f14cca2f9f61c","last_reissued_at":"2026-07-05T05:12:28.001610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:28.001610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.08445","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":"2026-07-05T05:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCrEIWdI1kvdR2VFekgnKBlSJHuEUdr3/Jp2lMFI+ABUkam3CqSk1NMxRMw1lCHdu7uaJuZ9NDohf/nTfUUKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:47:09.899641Z"},"content_sha256":"f594dcbc4d1052eb866e37ef3a2fc7bcbe11f8782fc0de42939845512c839dcf","schema_version":"1.0","event_id":"sha256:f594dcbc4d1052eb866e37ef3a2fc7bcbe11f8782fc0de42939845512c839dcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YQEXNNADVOYF2CRDUAQBRKG7UJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Matt Gardner, Sameer Singh, Shivanshu Gupta","submitted_at":"2022-03-16T07:41:27Z","abstract_excerpt":"A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different approach: training on instances with diverse structures. We propose a model-agnostic algorithm for subsampling such sets of instances from a labeled instance pool with structured outputs. Evaluating on both compositional template splits and traditional IID splits of 5 semantic parsing datasets of varying complexity, we show that st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08445","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/2203.08445/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":"2026-07-05T05:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ktY5lTKO/0o6OG+l7go69i0RjRJU1FihaSe5WI5VAAY7nd/z+bgk/wB29t9ALTfPAQ6d+GnbgvWvxqQydKORBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:47:09.901388Z"},"content_sha256":"fe0eb526525e7ed8e4cb37d7fdd278cc6b1b5935caa79968938172ac8f5c3174","schema_version":"1.0","event_id":"sha256:fe0eb526525e7ed8e4cb37d7fdd278cc6b1b5935caa79968938172ac8f5c3174"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/bundle.json","state_url":"https://pith.science/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/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":"2026-08-17T22:47:09Z","links":{"resolver":"https://pith.science/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ","bundle":"https://pith.science/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/bundle.json","state":"https://pith.science/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQEXNNADVOYF2CRDUAQBRKG7UJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YQEXNNADVOYF2CRDUAQBRKG7UJ","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":"b6de79cc5fee76e395028b96772395b577c33e52101bada93cca5830ce1bff75","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:41:27Z","title_canon_sha256":"3f0c65e9c22076e314895bc355cadbf8d611a119361bb944ec4377699f29b540"},"schema_version":"1.0","source":{"id":"2203.08445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08445","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08445v2","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08445","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"YQEXNNADVOYF","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"YQEXNNADVOYF2CRD","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"YQEXNNAD","created_at":"2026-07-05T05:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:fe0eb526525e7ed8e4cb37d7fdd278cc6b1b5935caa79968938172ac8f5c3174","target":"graph","created_at":"2026-07-05T05:12:28Z","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/2203.08445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different approach: training on instances with diverse structures. We propose a model-agnostic algorithm for subsampling such sets of instances from a labeled instance pool with structured outputs. Evaluating on both compositional template splits and traditional IID splits of 5 semantic parsing datasets of varying complexity, we show that st","authors_text":"Matt Gardner, Sameer Singh, Shivanshu Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:41:27Z","title":"Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08445","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:f594dcbc4d1052eb866e37ef3a2fc7bcbe11f8782fc0de42939845512c839dcf","target":"record","created_at":"2026-07-05T05:12:28Z","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":"b6de79cc5fee76e395028b96772395b577c33e52101bada93cca5830ce1bff75","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:41:27Z","title_canon_sha256":"3f0c65e9c22076e314895bc355cadbf8d611a119361bb944ec4377699f29b540"},"schema_version":"1.0","source":{"id":"2203.08445","kind":"arxiv","version":2}},"canonical_sha256":"c40976b403abb05d0a23a02018a8dfa242b94e437d569251310f14cca2f9f61c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40976b403abb05d0a23a02018a8dfa242b94e437d569251310f14cca2f9f61c","first_computed_at":"2026-07-05T05:12:28.001610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:28.001610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tsQbpp8Espd5X/fRkgJiTLSwI2vHaIhNomllMORT+JeUK61mqF55TCcGaXG/7G4aDKg0Rzz8csVZS/gDZOHqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:28.002020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f594dcbc4d1052eb866e37ef3a2fc7bcbe11f8782fc0de42939845512c839dcf","sha256:fe0eb526525e7ed8e4cb37d7fdd278cc6b1b5935caa79968938172ac8f5c3174"],"state_sha256":"6781794c039b25e19ecce57032c47c5969dd0f2973002038b5254e45cf992b54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlV5JjzzEgE4JfJKvLDi318tkU4L4jTSFNtNeJ76FFvA+pNsgom2Pjm1cO7eJdRx/9AfUtbBzubxYqiYA/GzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:47:09.908282Z","bundle_sha256":"e465538c51b1394cd957cf5b6fc4f76c2f4ff0e95d540f7f9b7fd4d04c7c5a05"}}