{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NOBWJMCOWLFUKP52GHN7XH63UF","short_pith_number":"pith:NOBWJMCO","canonical_record":{"source":{"id":"1802.00757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T16:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"45841e2639ee1c2b548fd5a16020073805d08bff0b479fa130cbeb24b91b5d59","abstract_canon_sha256":"adebee6addeb7030fa8d3e02ccae5eb80f8488201e1345a8b2bbb2bad894cb46"},"schema_version":"1.0"},"canonical_sha256":"6b8364b04eb2cb453fba31dbfb9fdba15061dd4801a9fd1c925f3146ca79ea63","source":{"kind":"arxiv","id":"1802.00757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00757","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00757v2","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00757","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"NOBWJMCOWLFU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOBWJMCOWLFUKP52","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOBWJMCO","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NOBWJMCOWLFUKP52GHN7XH63UF","target":"record","payload":{"canonical_record":{"source":{"id":"1802.00757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T16:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"45841e2639ee1c2b548fd5a16020073805d08bff0b479fa130cbeb24b91b5d59","abstract_canon_sha256":"adebee6addeb7030fa8d3e02ccae5eb80f8488201e1345a8b2bbb2bad894cb46"},"schema_version":"1.0"},"canonical_sha256":"6b8364b04eb2cb453fba31dbfb9fdba15061dd4801a9fd1c925f3146ca79ea63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:18.007680Z","signature_b64":"sSdh01jtSsfGif4rh63ufJHQCzOI9dtEe/z0DWP+ApwML+NUZxIoGC2+F/UBXeI5jK0mWA546BOYixrEWJBdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8364b04eb2cb453fba31dbfb9fdba15061dd4801a9fd1c925f3146ca79ea63","last_reissued_at":"2026-05-18T00:11:18.006890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:18.006890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.00757","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":"2026-05-18T00:11:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCEunc5iCOG/UKSt01OWbJWL+3XJAq/19plPpd0nOiTLLAUPRqiscJ//txKTp04OQGxZS7QzzKIV+1YP5uYWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:22:42.648908Z"},"content_sha256":"95a616a5f7e2b9a41c975eed43925a19287751fb87af315cf617a96c304a6a0e","schema_version":"1.0","event_id":"sha256:95a616a5f7e2b9a41c975eed43925a19287751fb87af315cf617a96c304a6a0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NOBWJMCOWLFUKP52GHN7XH63UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Submodularity-Inspired Data Selection for Goal-Oriented Chatbot Training Based on Sentence Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreea Hossmann, Claudiu Musat, Michael Baeriswyl, Mladen Dimovski, Vladimir Ilievski","submitted_at":"2018-02-02T16:26:39Z","abstract_excerpt":"Spoken language understanding (SLU) systems, such as goal-oriented chatbots or personal assistants, rely on an initial natural language understanding (NLU) module to determine the intent and to extract the relevant information from the user queries they take as input. SLU systems usually help users to solve problems in relatively narrow domains and require a large amount of in-domain training data. This leads to significant data availability issues that inhibit the development of successful systems. To alleviate this problem, we propose a technique of data selection in the low-data regime that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00757","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":""},"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":"2026-05-18T00:11:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QE9AXr53yvI87uQCTviTXNMBskh0nxP26GPW+FyWNW1DA3Gn8kfX6LNodSZYj4OAIQRjzuGXhrh8kWYJSOTnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:22:42.649476Z"},"content_sha256":"8b7a6028ae80b5e6391880581718f5a302f1314672cef34a6d6b0b29c29c65dd","schema_version":"1.0","event_id":"sha256:8b7a6028ae80b5e6391880581718f5a302f1314672cef34a6d6b0b29c29c65dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOBWJMCOWLFUKP52GHN7XH63UF/bundle.json","state_url":"https://pith.science/pith/NOBWJMCOWLFUKP52GHN7XH63UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOBWJMCOWLFUKP52GHN7XH63UF/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":"2026-06-05T00:22:42Z","links":{"resolver":"https://pith.science/pith/NOBWJMCOWLFUKP52GHN7XH63UF","bundle":"https://pith.science/pith/NOBWJMCOWLFUKP52GHN7XH63UF/bundle.json","state":"https://pith.science/pith/NOBWJMCOWLFUKP52GHN7XH63UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOBWJMCOWLFUKP52GHN7XH63UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NOBWJMCOWLFUKP52GHN7XH63UF","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":"adebee6addeb7030fa8d3e02ccae5eb80f8488201e1345a8b2bbb2bad894cb46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T16:26:39Z","title_canon_sha256":"45841e2639ee1c2b548fd5a16020073805d08bff0b479fa130cbeb24b91b5d59"},"schema_version":"1.0","source":{"id":"1802.00757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00757","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00757v2","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00757","created_at":"2026-05-18T00:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"NOBWJMCOWLFU","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOBWJMCOWLFUKP52","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOBWJMCO","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:8b7a6028ae80b5e6391880581718f5a302f1314672cef34a6d6b0b29c29c65dd","target":"graph","created_at":"2026-05-18T00:11:18Z","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"},"paper":{"abstract_excerpt":"Spoken language understanding (SLU) systems, such as goal-oriented chatbots or personal assistants, rely on an initial natural language understanding (NLU) module to determine the intent and to extract the relevant information from the user queries they take as input. SLU systems usually help users to solve problems in relatively narrow domains and require a large amount of in-domain training data. This leads to significant data availability issues that inhibit the development of successful systems. To alleviate this problem, we propose a technique of data selection in the low-data regime that","authors_text":"Andreea Hossmann, Claudiu Musat, Michael Baeriswyl, Mladen Dimovski, Vladimir Ilievski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T16:26:39Z","title":"Submodularity-Inspired Data Selection for Goal-Oriented Chatbot Training Based on Sentence Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00757","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":"sha256:95a616a5f7e2b9a41c975eed43925a19287751fb87af315cf617a96c304a6a0e","target":"record","created_at":"2026-05-18T00:11:18Z","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":"adebee6addeb7030fa8d3e02ccae5eb80f8488201e1345a8b2bbb2bad894cb46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-02T16:26:39Z","title_canon_sha256":"45841e2639ee1c2b548fd5a16020073805d08bff0b479fa130cbeb24b91b5d59"},"schema_version":"1.0","source":{"id":"1802.00757","kind":"arxiv","version":2}},"canonical_sha256":"6b8364b04eb2cb453fba31dbfb9fdba15061dd4801a9fd1c925f3146ca79ea63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8364b04eb2cb453fba31dbfb9fdba15061dd4801a9fd1c925f3146ca79ea63","first_computed_at":"2026-05-18T00:11:18.006890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:18.006890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sSdh01jtSsfGif4rh63ufJHQCzOI9dtEe/z0DWP+ApwML+NUZxIoGC2+F/UBXeI5jK0mWA546BOYixrEWJBdCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:18.007680Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95a616a5f7e2b9a41c975eed43925a19287751fb87af315cf617a96c304a6a0e","sha256:8b7a6028ae80b5e6391880581718f5a302f1314672cef34a6d6b0b29c29c65dd"],"state_sha256":"357e4018db7c7945b502dca1116e52e919a930c430a229cc3e9009ff30c463f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0TU1qumDMdGAp9PJhhDDwXBNlp/MIu+dUkwmvdlVQ56GubBYgV1k3H0z6Titn3pAkoC/e3f0WzQojAjE3eACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:22:42.652131Z","bundle_sha256":"afbdf43ba5e41c08b5caf078fef4f1dc00b38666ece3cd876263579f70cfdcf2"}}