{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3GP5ROERRQIEC3ZY7YVGY4PPZA","short_pith_number":"pith:3GP5ROER","canonical_record":{"source":{"id":"2503.10698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:38:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"2232db7c647c0511dff3af09075ae39d142e8551707c18cf0757ac80b388fc71","abstract_canon_sha256":"b0ade5df649d693fe0cf133f47a242cf63e7b9c274fec638788aff076c3f37d6"},"schema_version":"1.0"},"canonical_sha256":"d99fd8b8918c10416f38fe2a6c71efc81c6e257f5a09e8d562c4e9528a3a3dfb","source":{"kind":"arxiv","id":"2503.10698","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10698","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10698v1","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10698","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"3GP5ROERRQIE","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"3GP5ROERRQIEC3ZY","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"3GP5ROER","created_at":"2026-07-05T10:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3GP5ROERRQIEC3ZY7YVGY4PPZA","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:38:57Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"2232db7c647c0511dff3af09075ae39d142e8551707c18cf0757ac80b388fc71","abstract_canon_sha256":"b0ade5df649d693fe0cf133f47a242cf63e7b9c274fec638788aff076c3f37d6"},"schema_version":"1.0"},"canonical_sha256":"d99fd8b8918c10416f38fe2a6c71efc81c6e257f5a09e8d562c4e9528a3a3dfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:03.984667Z","signature_b64":"qVij2uUpSeDQBZkFahfZOIDM84fq7gAPZI/Y6FmI6aag6oTSK62x7P13fzg0yTUD7QkFbWi0IIrt0hIUOufVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99fd8b8918c10416f38fe2a6c71efc81c6e257f5a09e8d562c4e9528a3a3dfb","last_reissued_at":"2026-07-05T10:31:03.983705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:03.983705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10698","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":"2026-07-05T10:31:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXQxAXnJ1/0oMzSRyewl3BH2SYeL1TzoN7+p5cIgxQwPtRJ6K3aTg/kWb16x9YetEnxQr3TjS9SyomlYDsScDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:56:55.775693Z"},"content_sha256":"9ecbfd8d70f6e7ba5c5eb0a0d4d918f893d3055140cb9882fe8b00c91fb9b179","schema_version":"1.0","event_id":"sha256:9ecbfd8d70f6e7ba5c5eb0a0d4d918f893d3055140cb9882fe8b00c91fb9b179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3GP5ROERRQIEC3ZY7YVGY4PPZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ordered Semantically Diverse Sampling for Textual Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ananya Singha, Arjun Radhakrishna, Ashish Tiwari, Mukul Singh","submitted_at":"2025-03-12T06:38:57Z","abstract_excerpt":"The goal of diversity sampling is to select a representative subset of data in a way that maximizes information contained in the subset while keeping its cardinality small. We introduce the ordered diverse sampling problem based on a new metric that measures the diversity in an ordered list of samples. We present a novel approach for generating ordered diverse samples for textual data that uses principal components on the embedding vectors. The proposed approach is simple and compared with existing approaches using the new metric. We transform standard text classification benchmarks into bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10698","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/2503.10698/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":"2026-07-05T10:31:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWTTFzi88XDCVeU595Od1ierjJ1573D6ntViZoHS5bNXL2A9b3T9GVmnRnfQTR5Slw1EamM3iA+BTH/+dovgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:56:55.776455Z"},"content_sha256":"c4e1e2a0b5b51c8a27f68e6110ec74a511fb9b2543d52d64245a2f48eed83a64","schema_version":"1.0","event_id":"sha256:c4e1e2a0b5b51c8a27f68e6110ec74a511fb9b2543d52d64245a2f48eed83a64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/bundle.json","state_url":"https://pith.science/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/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":"2026-08-01T00:56:55Z","links":{"resolver":"https://pith.science/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA","bundle":"https://pith.science/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/bundle.json","state":"https://pith.science/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GP5ROERRQIEC3ZY7YVGY4PPZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3GP5ROERRQIEC3ZY7YVGY4PPZA","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":"b0ade5df649d693fe0cf133f47a242cf63e7b9c274fec638788aff076c3f37d6","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:38:57Z","title_canon_sha256":"2232db7c647c0511dff3af09075ae39d142e8551707c18cf0757ac80b388fc71"},"schema_version":"1.0","source":{"id":"2503.10698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10698","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10698v1","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10698","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"3GP5ROERRQIE","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"3GP5ROERRQIEC3ZY","created_at":"2026-07-05T10:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"3GP5ROER","created_at":"2026-07-05T10:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:c4e1e2a0b5b51c8a27f68e6110ec74a511fb9b2543d52d64245a2f48eed83a64","target":"graph","created_at":"2026-07-05T10:31:03Z","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/2503.10698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of diversity sampling is to select a representative subset of data in a way that maximizes information contained in the subset while keeping its cardinality small. We introduce the ordered diverse sampling problem based on a new metric that measures the diversity in an ordered list of samples. We present a novel approach for generating ordered diverse samples for textual data that uses principal components on the embedding vectors. The proposed approach is simple and compared with existing approaches using the new metric. We transform standard text classification benchmarks into bench","authors_text":"Ananya Singha, Arjun Radhakrishna, Ashish Tiwari, Mukul Singh","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:38:57Z","title":"Ordered Semantically Diverse Sampling for Textual Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10698","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":"sha256:9ecbfd8d70f6e7ba5c5eb0a0d4d918f893d3055140cb9882fe8b00c91fb9b179","target":"record","created_at":"2026-07-05T10:31:03Z","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":"b0ade5df649d693fe0cf133f47a242cf63e7b9c274fec638788aff076c3f37d6","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:38:57Z","title_canon_sha256":"2232db7c647c0511dff3af09075ae39d142e8551707c18cf0757ac80b388fc71"},"schema_version":"1.0","source":{"id":"2503.10698","kind":"arxiv","version":1}},"canonical_sha256":"d99fd8b8918c10416f38fe2a6c71efc81c6e257f5a09e8d562c4e9528a3a3dfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d99fd8b8918c10416f38fe2a6c71efc81c6e257f5a09e8d562c4e9528a3a3dfb","first_computed_at":"2026-07-05T10:31:03.983705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:03.983705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVij2uUpSeDQBZkFahfZOIDM84fq7gAPZI/Y6FmI6aag6oTSK62x7P13fzg0yTUD7QkFbWi0IIrt0hIUOufVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:03.984667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ecbfd8d70f6e7ba5c5eb0a0d4d918f893d3055140cb9882fe8b00c91fb9b179","sha256:c4e1e2a0b5b51c8a27f68e6110ec74a511fb9b2543d52d64245a2f48eed83a64"],"state_sha256":"914d53d1beeeb55fb448467a352fb5231e4bbe364074878782efe4f747ce560b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDRRebA4mYpbpRYasBPswtZPqDMC1DQgN6LQrW6hhHqt8CJ4bdagBzHyYvDPwohAtpQTKzABB2BJ0N9d53+GDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T00:56:55.827717Z","bundle_sha256":"260c19a75e1b9793c5a36448841661fe119963d6fd8ad1192789cac02e50208c"}}