{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R45BMR2S7UXKWPCWKM3VNAKBDN","short_pith_number":"pith:R45BMR2S","canonical_record":{"source":{"id":"2402.14888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T09:43:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5e3470cf5d7a44b44b11b0091796f60ca3410a23fc77d07f6fd263ea7d5bbbc4","abstract_canon_sha256":"edb72b2aa901e92534178228e04ad12ad7770cd38b9c057a52bb3ba7ed184911"},"schema_version":"1.0"},"canonical_sha256":"8f3a164752fd2eab3c5653375681411b6a6e94e450d3129359058c540731a509","source":{"kind":"arxiv","id":"2402.14888","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14888","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14888v1","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14888","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"R45BMR2S7UXK","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"R45BMR2S7UXKWPCW","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"R45BMR2S","created_at":"2026-07-05T07:48:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R45BMR2S7UXKWPCWKM3VNAKBDN","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T09:43:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5e3470cf5d7a44b44b11b0091796f60ca3410a23fc77d07f6fd263ea7d5bbbc4","abstract_canon_sha256":"edb72b2aa901e92534178228e04ad12ad7770cd38b9c057a52bb3ba7ed184911"},"schema_version":"1.0"},"canonical_sha256":"8f3a164752fd2eab3c5653375681411b6a6e94e450d3129359058c540731a509","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:19.356216Z","signature_b64":"ApQjCjuNOq5t90izCufEZQdERncLBTwBmELa9W+xtqZ7MpLoiG9kgROLiyMoH7x8pU6Ejcz5mCf6QlLCMdoyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3a164752fd2eab3c5653375681411b6a6e94e450d3129359058c540731a509","last_reissued_at":"2026-07-05T07:48:19.355766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:19.355766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14888","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":"2026-07-05T07:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XK3jjzHfM3wITs3Rnrf4d8Jr7Ude00SkBZkyaU1rr6psB4y3ZSYqKyLjzyBy1PiNFD4y1slhzltgKvaJBl//AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:54:38.255778Z"},"content_sha256":"fbea8ccd1e80775dca71fab6e5c48484db16c8b6b6d5211b3461ca22e957c688","schema_version":"1.0","event_id":"sha256:fbea8ccd1e80775dca71fab6e5c48484db16c8b6b6d5211b3461ca22e957c688"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R45BMR2S7UXKWPCWKM3VNAKBDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient data selection employing Semantic Similarity-based Graph Structures for model training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Roxana Petcu, Subhadeep Maji","submitted_at":"2024-02-22T09:43:53Z","abstract_excerpt":"Recent developments in natural language processing (NLP) have highlighted the need for substantial amounts of data for models to capture textual information accurately. This raises concerns regarding the computational resources and time required for training such models. This paper introduces Semantics for data SAliency in Model performance Estimation (SeSaME). It is an efficient data sampling mechanism solely based on textual information without passing the data through a compute-heavy model or other intensive pre-processing transformations. The application of this approach is demonstrated in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14888","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/2402.14888/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":"2026-07-05T07:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Dtlzn3Eo1vBVtPAYwAjGibaO+0Uscp0mbv0kj6tgA58WXIo2e/VY7Rbd1BV/n83BL4PDP3Eh7ZTKls4/2oVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:54:38.256347Z"},"content_sha256":"8bbcec2e2a4ea5152236133861dac29cbafc9d8f33757e8435b59ecb14f56070","schema_version":"1.0","event_id":"sha256:8bbcec2e2a4ea5152236133861dac29cbafc9d8f33757e8435b59ecb14f56070"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/bundle.json","state_url":"https://pith.science/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/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":"2026-08-03T15:54:38Z","links":{"resolver":"https://pith.science/pith/R45BMR2S7UXKWPCWKM3VNAKBDN","bundle":"https://pith.science/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/bundle.json","state":"https://pith.science/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R45BMR2S7UXKWPCWKM3VNAKBDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R45BMR2S7UXKWPCWKM3VNAKBDN","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":"edb72b2aa901e92534178228e04ad12ad7770cd38b9c057a52bb3ba7ed184911","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T09:43:53Z","title_canon_sha256":"5e3470cf5d7a44b44b11b0091796f60ca3410a23fc77d07f6fd263ea7d5bbbc4"},"schema_version":"1.0","source":{"id":"2402.14888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14888","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14888v1","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14888","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"R45BMR2S7UXK","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"R45BMR2S7UXKWPCW","created_at":"2026-07-05T07:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"R45BMR2S","created_at":"2026-07-05T07:48:19Z"}],"graph_snapshots":[{"event_id":"sha256:8bbcec2e2a4ea5152236133861dac29cbafc9d8f33757e8435b59ecb14f56070","target":"graph","created_at":"2026-07-05T07:48:19Z","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/2402.14888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent developments in natural language processing (NLP) have highlighted the need for substantial amounts of data for models to capture textual information accurately. This raises concerns regarding the computational resources and time required for training such models. This paper introduces Semantics for data SAliency in Model performance Estimation (SeSaME). It is an efficient data sampling mechanism solely based on textual information without passing the data through a compute-heavy model or other intensive pre-processing transformations. The application of this approach is demonstrated in","authors_text":"Roxana Petcu, Subhadeep Maji","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T09:43:53Z","title":"Efficient data selection employing Semantic Similarity-based Graph Structures for model training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14888","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:fbea8ccd1e80775dca71fab6e5c48484db16c8b6b6d5211b3461ca22e957c688","target":"record","created_at":"2026-07-05T07:48:19Z","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":"edb72b2aa901e92534178228e04ad12ad7770cd38b9c057a52bb3ba7ed184911","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T09:43:53Z","title_canon_sha256":"5e3470cf5d7a44b44b11b0091796f60ca3410a23fc77d07f6fd263ea7d5bbbc4"},"schema_version":"1.0","source":{"id":"2402.14888","kind":"arxiv","version":1}},"canonical_sha256":"8f3a164752fd2eab3c5653375681411b6a6e94e450d3129359058c540731a509","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f3a164752fd2eab3c5653375681411b6a6e94e450d3129359058c540731a509","first_computed_at":"2026-07-05T07:48:19.355766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:19.355766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ApQjCjuNOq5t90izCufEZQdERncLBTwBmELa9W+xtqZ7MpLoiG9kgROLiyMoH7x8pU6Ejcz5mCf6QlLCMdoyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:19.356216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbea8ccd1e80775dca71fab6e5c48484db16c8b6b6d5211b3461ca22e957c688","sha256:8bbcec2e2a4ea5152236133861dac29cbafc9d8f33757e8435b59ecb14f56070"],"state_sha256":"8d3dcdbb149feecc07e96790400774b077dc7b2a3abb2b559ef81b0ca8ebfe7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7I9ERbTAGTWFpODnXqSyrsOEKu7luQcbMZ5UEPgBpH/qQwJZnXaM7ac4AhcJycLiV03saQd8J9WxLeUwHrwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:54:38.263361Z","bundle_sha256":"8c4e6cb93e69dde7c5c7e5320333da7abd207e5679490cee7013a0fb2350b613"}}