{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2KWX7LVYQWBDQULSDJKGDTK3CR","short_pith_number":"pith:2KWX7LVY","canonical_record":{"source":{"id":"2210.05721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T18:28:19Z","cross_cats_sorted":[],"title_canon_sha256":"2eaa215499fa2bb4ca68ff056aaf91dafa6c1cbf73f9f8ec29c79a410b1ccd83","abstract_canon_sha256":"0495b021f865c93ed3b30319b0d99f77d572db203a9b3a2d33cee2722ebfb811"},"schema_version":"1.0"},"canonical_sha256":"d2ad7faeb885823851721a5461cd5b145ee50fa7810d392498e714a1166814a1","source":{"kind":"arxiv","id":"2210.05721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05721","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05721v1","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05721","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"2KWX7LVYQWBD","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"2KWX7LVYQWBDQULS","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"2KWX7LVY","created_at":"2026-07-05T05:05:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2KWX7LVYQWBDQULSDJKGDTK3CR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T18:28:19Z","cross_cats_sorted":[],"title_canon_sha256":"2eaa215499fa2bb4ca68ff056aaf91dafa6c1cbf73f9f8ec29c79a410b1ccd83","abstract_canon_sha256":"0495b021f865c93ed3b30319b0d99f77d572db203a9b3a2d33cee2722ebfb811"},"schema_version":"1.0"},"canonical_sha256":"d2ad7faeb885823851721a5461cd5b145ee50fa7810d392498e714a1166814a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:52.178425Z","signature_b64":"3YGcJh0EV/WvTXElJLkQjxU2OBCWiEDu127nVDzTnd8sAX/MpwQEz7frocxLRwjDScih0bx7ZbUT93/nJVYICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2ad7faeb885823851721a5461cd5b145ee50fa7810d392498e714a1166814a1","last_reissued_at":"2026-07-05T05:05:52.177964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:52.177964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05721","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":"2026-07-05T05:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"faPUY/YLyjmUGaxRnn6sUKFc+Fwn/NGvwYliKPnsyKHo4wL++eQEh7cRilxnadivJsQKLKCBfFGMhjQh0hCUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:33:02.377354Z"},"content_sha256":"5a7782fd3fa9de65d8e134ab8dc36fddb047a9de2fe4e3e08a3e99c4a58ea22a","schema_version":"1.0","event_id":"sha256:5a7782fd3fa9de65d8e134ab8dc36fddb047a9de2fe4e3e08a3e99c4a58ea22a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2KWX7LVYQWBDQULSDJKGDTK3CR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariadna Quattoni, Audi Primadhanty, C\\'esar Gonz\\'alez-Guti\\'errez, Francesco Cazzaro","submitted_at":"2022-10-11T18:28:19Z","abstract_excerpt":"Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation budgets the choice of data representation is key. The goal of this paper is to better understand why this is so. With this goal in mind, we propose a metric that measures the extent to which a given representation is structurally aligned with a task. We conduct experiments on several text classification datasets testing a variety of models and representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05721","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/2210.05721/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":"2026-07-05T05:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMtkqLYcKCmw8lAHxQWYCBgrvFgTyp25Ch/ChGy7Wq2ceurRRAAM3DX64dJCy8NgRZ2njFPUQ64CQ7PbTdb3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:33:02.377737Z"},"content_sha256":"504b6e27412c98198af3acf02ad124989af3ac04fe026dfeb6d8695864790fd2","schema_version":"1.0","event_id":"sha256:504b6e27412c98198af3acf02ad124989af3ac04fe026dfeb6d8695864790fd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/bundle.json","state_url":"https://pith.science/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/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":"2026-08-23T09:33:02Z","links":{"resolver":"https://pith.science/pith/2KWX7LVYQWBDQULSDJKGDTK3CR","bundle":"https://pith.science/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/bundle.json","state":"https://pith.science/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KWX7LVYQWBDQULSDJKGDTK3CR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2KWX7LVYQWBDQULSDJKGDTK3CR","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":"0495b021f865c93ed3b30319b0d99f77d572db203a9b3a2d33cee2722ebfb811","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T18:28:19Z","title_canon_sha256":"2eaa215499fa2bb4ca68ff056aaf91dafa6c1cbf73f9f8ec29c79a410b1ccd83"},"schema_version":"1.0","source":{"id":"2210.05721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05721","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05721v1","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05721","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"2KWX7LVYQWBD","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"2KWX7LVYQWBDQULS","created_at":"2026-07-05T05:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"2KWX7LVY","created_at":"2026-07-05T05:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:504b6e27412c98198af3acf02ad124989af3ac04fe026dfeb6d8695864790fd2","target":"graph","created_at":"2026-07-05T05:05:52Z","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/2210.05721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation budgets the choice of data representation is key. The goal of this paper is to better understand why this is so. With this goal in mind, we propose a metric that measures the extent to which a given representation is structurally aligned with a task. We conduct experiments on several text classification datasets testing a variety of models and representatio","authors_text":"Ariadna Quattoni, Audi Primadhanty, C\\'esar Gonz\\'alez-Guti\\'errez, Francesco Cazzaro","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T18:28:19Z","title":"Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05721","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":"sha256:5a7782fd3fa9de65d8e134ab8dc36fddb047a9de2fe4e3e08a3e99c4a58ea22a","target":"record","created_at":"2026-07-05T05:05:52Z","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":"0495b021f865c93ed3b30319b0d99f77d572db203a9b3a2d33cee2722ebfb811","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T18:28:19Z","title_canon_sha256":"2eaa215499fa2bb4ca68ff056aaf91dafa6c1cbf73f9f8ec29c79a410b1ccd83"},"schema_version":"1.0","source":{"id":"2210.05721","kind":"arxiv","version":1}},"canonical_sha256":"d2ad7faeb885823851721a5461cd5b145ee50fa7810d392498e714a1166814a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2ad7faeb885823851721a5461cd5b145ee50fa7810d392498e714a1166814a1","first_computed_at":"2026-07-05T05:05:52.177964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:52.177964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3YGcJh0EV/WvTXElJLkQjxU2OBCWiEDu127nVDzTnd8sAX/MpwQEz7frocxLRwjDScih0bx7ZbUT93/nJVYICw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:52.178425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a7782fd3fa9de65d8e134ab8dc36fddb047a9de2fe4e3e08a3e99c4a58ea22a","sha256:504b6e27412c98198af3acf02ad124989af3ac04fe026dfeb6d8695864790fd2"],"state_sha256":"ccbcac20246a1b98f232d26334c537f6f7009ec498486fdfe01bb0384afa26b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XkIca4GSQHVP6oRA5jWHYZyRwSvmhxRk8aufuCXVz5ShfOMiH7Rjz2wODaUnvALlEZ6IxSw+bZKCZUvF5F6hDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T09:33:02.380409Z","bundle_sha256":"bf63d803d036bd46df02e9e034254f5e738dcba09eeb567ef13aa50b23320223"}}