{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:K5WLYCN2NVDV3B4KEB7QTSMVR4","short_pith_number":"pith:K5WLYCN2","canonical_record":{"source":{"id":"1802.06861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T07:42:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"921b46732fa709960ec05e38a3083f22241b392d533b0da4e619aaa324077ea1","abstract_canon_sha256":"e9717b15b2f66fef34c5143aed79168cacc7bb250062d09efe414e91a11a3862"},"schema_version":"1.0"},"canonical_sha256":"576cbc09ba6d475d878a207f09c9958f1d5a0a61abde04a7c3e8856856cbf913","source":{"kind":"arxiv","id":"1802.06861","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06861","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06861v1","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06861","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"K5WLYCN2NVDV","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K5WLYCN2NVDV3B4K","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K5WLYCN2","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:K5WLYCN2NVDV3B4KEB7QTSMVR4","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T07:42:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"921b46732fa709960ec05e38a3083f22241b392d533b0da4e619aaa324077ea1","abstract_canon_sha256":"e9717b15b2f66fef34c5143aed79168cacc7bb250062d09efe414e91a11a3862"},"schema_version":"1.0"},"canonical_sha256":"576cbc09ba6d475d878a207f09c9958f1d5a0a61abde04a7c3e8856856cbf913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:54.142770Z","signature_b64":"1WfD1UFRzqAOkJ8YVw/a4voj3BH6mAj+iYXPUDWX9MsiZUhPSKiEC2wm69sK2DHvYy+MA4CE05O8hOeZoKtPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"576cbc09ba6d475d878a207f09c9958f1d5a0a61abde04a7c3e8856856cbf913","last_reissued_at":"2026-05-18T00:22:54.142154Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:54.142154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06861","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":"2026-05-18T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nelx8GpRj/olajl+jTOxltACaolME9CXwr5oFgpkHkxYT+xrI4+44fJpBm5AnSnPyKm57eRUjKEq4vmOnrzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:06:17.334275Z"},"content_sha256":"b1a4ef801f4ef5756de0989b7035c072fcd245900027102b725b1d8b9f3b46c4","schema_version":"1.0","event_id":"sha256:b1a4ef801f4ef5756de0989b7035c072fcd245900027102b725b1d8b9f3b46c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:K5WLYCN2NVDV3B4KEB7QTSMVR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Horacio Franco, Vikramjit Mitra","submitted_at":"2018-02-16T07:42:35Z","abstract_excerpt":"Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the label for model adaptation. However, assessing the goodness of the hypothesis can be difficult, and an erroneous hypothesis can lead to poorly trained models. In such cases, a strategy to select data having reliable hypothesis can ensure better model adaptation. This work proposes a data-selection strategy for DNN model adaptation, where DNN output layer ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06861","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":""},"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":"2026-05-18T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDW/INezFFLecf+Kjk/smuRWizvwjVPbDboOjiZ0bQYJAXjT2lKBjurct01wrBdritbKIXc5GuEitgDvUZhqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:06:17.334650Z"},"content_sha256":"fa9ed5fc84ad5ee9429b1e12d418e4afcacce9f814a9f42cf001f5ed11e09a2a","schema_version":"1.0","event_id":"sha256:fa9ed5fc84ad5ee9429b1e12d418e4afcacce9f814a9f42cf001f5ed11e09a2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/bundle.json","state_url":"https://pith.science/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/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":"2026-06-01T16:06:17Z","links":{"resolver":"https://pith.science/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4","bundle":"https://pith.science/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/bundle.json","state":"https://pith.science/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5WLYCN2NVDV3B4KEB7QTSMVR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K5WLYCN2NVDV3B4KEB7QTSMVR4","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":"e9717b15b2f66fef34c5143aed79168cacc7bb250062d09efe414e91a11a3862","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T07:42:35Z","title_canon_sha256":"921b46732fa709960ec05e38a3083f22241b392d533b0da4e619aaa324077ea1"},"schema_version":"1.0","source":{"id":"1802.06861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06861","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06861v1","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06861","created_at":"2026-05-18T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"K5WLYCN2NVDV","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K5WLYCN2NVDV3B4K","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K5WLYCN2","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:fa9ed5fc84ad5ee9429b1e12d418e4afcacce9f814a9f42cf001f5ed11e09a2a","target":"graph","created_at":"2026-05-18T00:22:54Z","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":"Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the label for model adaptation. However, assessing the goodness of the hypothesis can be difficult, and an erroneous hypothesis can lead to poorly trained models. In such cases, a strategy to select data having reliable hypothesis can ensure better model adaptation. This work proposes a data-selection strategy for DNN model adaptation, where DNN output layer ac","authors_text":"Horacio Franco, Vikramjit Mitra","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T07:42:35Z","title":"Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06861","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:b1a4ef801f4ef5756de0989b7035c072fcd245900027102b725b1d8b9f3b46c4","target":"record","created_at":"2026-05-18T00:22:54Z","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":"e9717b15b2f66fef34c5143aed79168cacc7bb250062d09efe414e91a11a3862","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T07:42:35Z","title_canon_sha256":"921b46732fa709960ec05e38a3083f22241b392d533b0da4e619aaa324077ea1"},"schema_version":"1.0","source":{"id":"1802.06861","kind":"arxiv","version":1}},"canonical_sha256":"576cbc09ba6d475d878a207f09c9958f1d5a0a61abde04a7c3e8856856cbf913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"576cbc09ba6d475d878a207f09c9958f1d5a0a61abde04a7c3e8856856cbf913","first_computed_at":"2026-05-18T00:22:54.142154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:54.142154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1WfD1UFRzqAOkJ8YVw/a4voj3BH6mAj+iYXPUDWX9MsiZUhPSKiEC2wm69sK2DHvYy+MA4CE05O8hOeZoKtPBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:54.142770Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1a4ef801f4ef5756de0989b7035c072fcd245900027102b725b1d8b9f3b46c4","sha256:fa9ed5fc84ad5ee9429b1e12d418e4afcacce9f814a9f42cf001f5ed11e09a2a"],"state_sha256":"3d044d10af1dda10d15e382e7ce0025b67639dbd293e87f7209b9b88a51aa737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EImyY3gtAUE6IjZJVGHqk6u/kH8XEYaAqb+nMHxpn3yyomkG1Vi2xWTs8C7XyWJk4je7OlySs64g9+fBVDxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:06:17.336624Z","bundle_sha256":"18f139b4ee74d77e0cc9bd10ce25c662c1062934bae96ab33a6372b79b903a76"}}