{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AKEKEA32MCKKTRKC3LV4VU3PAS","short_pith_number":"pith:AKEKEA32","canonical_record":{"source":{"id":"2011.11387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-23T13:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"3fddc7cad641883aee514f5b072550cd2a325964547368a591ee994fae927d43","abstract_canon_sha256":"c937053a93d4f0948e7b347ea6bb8ab101d5fb622fbe9e12cba16ccb1df51ee9"},"schema_version":"1.0"},"canonical_sha256":"0288a2037a6094a9c542daebcad36f04b0753f062179e74cb9baca8eaa274d92","source":{"kind":"arxiv","id":"2011.11387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11387","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11387v1","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11387","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_12","alias_value":"AKEKEA32MCKK","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_16","alias_value":"AKEKEA32MCKKTRKC","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_8","alias_value":"AKEKEA32","created_at":"2026-07-05T01:53:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AKEKEA32MCKKTRKC3LV4VU3PAS","target":"record","payload":{"canonical_record":{"source":{"id":"2011.11387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-23T13:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"3fddc7cad641883aee514f5b072550cd2a325964547368a591ee994fae927d43","abstract_canon_sha256":"c937053a93d4f0948e7b347ea6bb8ab101d5fb622fbe9e12cba16ccb1df51ee9"},"schema_version":"1.0"},"canonical_sha256":"0288a2037a6094a9c542daebcad36f04b0753f062179e74cb9baca8eaa274d92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:42.140579Z","signature_b64":"WVcQRT04h/qmhYIlO05o/3+N/vsGnyFaR2z4veUuDMxiKe/uzWxJi2PJaxfcYUaRvO/bbUghyoGaQsvGYu32CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0288a2037a6094a9c542daebcad36f04b0753f062179e74cb9baca8eaa274d92","last_reissued_at":"2026-07-05T01:53:42.140191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:42.140191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.11387","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":"2026-07-05T01:53:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AMWdQPL18VeywjTSRM/y4sNG4OJx7itX7zvXKHt44RgIz8hIl2VmGrlqsPo77XLbvGnKZQ4OkJiS4hjObLxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:47:33.869605Z"},"content_sha256":"090ce0859a8d6056257c8eb550e0f0d6c4c839cb0e97cc14b5cea45e2c2b756a","schema_version":"1.0","event_id":"sha256:090ce0859a8d6056257c8eb550e0f0d6c4c839cb0e97cc14b5cea45e2c2b756a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AKEKEA32MCKKTRKC3LV4VU3PAS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Prakamya Mishra","submitted_at":"2020-11-23T13:29:16Z","abstract_excerpt":"In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word using its contextual spoken word's speech and text, such that the model encodes its meaningful latent representations. Unlike existing work, we have used text along with speech for auditory representation learning to capture semantical and syntactical information along with the acoustic and temporal information. The lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11387","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/2011.11387/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":"2026-07-05T01:53:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwxxjgvcI8+vbRE6BgwveK0ng8UlUvKkr1S3u97DT+D7KExEjXs/gbbO2+KqY4nktEjZK2xzbeCVqqHgHZkqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:47:33.870120Z"},"content_sha256":"44d3238cdbe9b925bb4b9fc89760bd3340ccad2424c873aa4d2b63e0a888aabc","schema_version":"1.0","event_id":"sha256:44d3238cdbe9b925bb4b9fc89760bd3340ccad2424c873aa4d2b63e0a888aabc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/bundle.json","state_url":"https://pith.science/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/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":"2026-08-06T02:47:33Z","links":{"resolver":"https://pith.science/pith/AKEKEA32MCKKTRKC3LV4VU3PAS","bundle":"https://pith.science/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/bundle.json","state":"https://pith.science/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKEKEA32MCKKTRKC3LV4VU3PAS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AKEKEA32MCKKTRKC3LV4VU3PAS","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":"c937053a93d4f0948e7b347ea6bb8ab101d5fb622fbe9e12cba16ccb1df51ee9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-23T13:29:16Z","title_canon_sha256":"3fddc7cad641883aee514f5b072550cd2a325964547368a591ee994fae927d43"},"schema_version":"1.0","source":{"id":"2011.11387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11387","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11387v1","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11387","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_12","alias_value":"AKEKEA32MCKK","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_16","alias_value":"AKEKEA32MCKKTRKC","created_at":"2026-07-05T01:53:42Z"},{"alias_kind":"pith_short_8","alias_value":"AKEKEA32","created_at":"2026-07-05T01:53:42Z"}],"graph_snapshots":[{"event_id":"sha256:44d3238cdbe9b925bb4b9fc89760bd3340ccad2424c873aa4d2b63e0a888aabc","target":"graph","created_at":"2026-07-05T01:53:42Z","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/2011.11387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a novel multi-modal deep neural network architecture that uses speech and text entanglement for learning phonetically sound spoken-word representations. STEPs-RL is trained in a supervised manner to predict the phonetic sequence of a target spoken-word using its contextual spoken word's speech and text, such that the model encodes its meaningful latent representations. Unlike existing work, we have used text along with speech for auditory representation learning to capture semantical and syntactical information along with the acoustic and temporal information. The lat","authors_text":"Prakamya Mishra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-23T13:29:16Z","title":"STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11387","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":"sha256:090ce0859a8d6056257c8eb550e0f0d6c4c839cb0e97cc14b5cea45e2c2b756a","target":"record","created_at":"2026-07-05T01:53:42Z","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":"c937053a93d4f0948e7b347ea6bb8ab101d5fb622fbe9e12cba16ccb1df51ee9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-23T13:29:16Z","title_canon_sha256":"3fddc7cad641883aee514f5b072550cd2a325964547368a591ee994fae927d43"},"schema_version":"1.0","source":{"id":"2011.11387","kind":"arxiv","version":1}},"canonical_sha256":"0288a2037a6094a9c542daebcad36f04b0753f062179e74cb9baca8eaa274d92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0288a2037a6094a9c542daebcad36f04b0753f062179e74cb9baca8eaa274d92","first_computed_at":"2026-07-05T01:53:42.140191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:42.140191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVcQRT04h/qmhYIlO05o/3+N/vsGnyFaR2z4veUuDMxiKe/uzWxJi2PJaxfcYUaRvO/bbUghyoGaQsvGYu32CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:42.140579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.11387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:090ce0859a8d6056257c8eb550e0f0d6c4c839cb0e97cc14b5cea45e2c2b756a","sha256:44d3238cdbe9b925bb4b9fc89760bd3340ccad2424c873aa4d2b63e0a888aabc"],"state_sha256":"226b23304810e964504b03357fd93512d5d1bb4029cdf0f901a865520ee979d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gk2WU0YkXmz2jl9CD1jCTI2pccJr9UMCMfa3qvDjuG9G9NbyIxxRstk7GDXVPb8lr3b60yMNx0Uh51eXhIKiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:47:33.874811Z","bundle_sha256":"24f5058064d0a8873f5f2d1426ccf9f8d16b7a6127b0e3381dc03036bb901d94"}}