{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RLAY6RIYUA3K7NBATOUYUOSCWG","short_pith_number":"pith:RLAY6RIY","canonical_record":{"source":{"id":"2007.06028","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T16:19:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6159a26d526e3663654fc59cf6234798e97b44e376a13d4328b23627ae2f098e","abstract_canon_sha256":"c51a3a6bc861359bd77db762791cf7b3a4eeacf8f7629c9ad33727b8d993452f"},"schema_version":"1.0"},"canonical_sha256":"8ac18f4518a036afb4209ba98a3a42b1b141285e7714c6a3473c2d30bd6059f0","source":{"kind":"arxiv","id":"2007.06028","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06028","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06028v3","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06028","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"RLAY6RIYUA3K","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"RLAY6RIYUA3K7NBA","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"RLAY6RIY","created_at":"2026-07-05T03:03:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RLAY6RIYUA3K7NBATOUYUOSCWG","target":"record","payload":{"canonical_record":{"source":{"id":"2007.06028","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T16:19:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6159a26d526e3663654fc59cf6234798e97b44e376a13d4328b23627ae2f098e","abstract_canon_sha256":"c51a3a6bc861359bd77db762791cf7b3a4eeacf8f7629c9ad33727b8d993452f"},"schema_version":"1.0"},"canonical_sha256":"8ac18f4518a036afb4209ba98a3a42b1b141285e7714c6a3473c2d30bd6059f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:05.958633Z","signature_b64":"DZuE3z0XrhEuq6ns7b1KwOF9gC5PA4K33ReuCK22JEiqeKROqca4kQvOXe2aqn8VQum+F8rZ9y16RXHCz/mNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac18f4518a036afb4209ba98a3a42b1b141285e7714c6a3473c2d30bd6059f0","last_reissued_at":"2026-07-05T03:03:05.958156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:05.958156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.06028","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOggbsbbPMyNSXOq8oCl28LNvspjpPecu0egDdxrVXECwg55JtU7Pakwsq3ndzYYwHzdMyhwJe8tWNnwH5XHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:09:39.058008Z"},"content_sha256":"8f80b3d302f099c89df0b398ae7e1fad603aa79c72d96fb5a8245e036de5ecad","schema_version":"1.0","event_id":"sha256:8f80b3d302f099c89df0b398ae7e1fad603aa79c72d96fb5a8245e036de5ecad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RLAY6RIYUA3K7NBATOUYUOSCWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Andy T. Liu, Hung-yi Lee, Shang-Wen Li","submitted_at":"2020-07-12T16:19:00Z","abstract_excerpt":"We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous methods, we use alteration along three orthogonal axes to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from their altered counterpart, where we use a stochastic policy to alter along various dimensions: time, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06028","kind":"arxiv","version":3},"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/2007.06028/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":"2026-07-05T03:03:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H91FlkLo6VH8DJCT7j5DKOUSEkLoBzMJFww/uIFpf+7J4BMHuTSIYOj9CeHOKITSzxbK+Uv8uDcYLeJK5xV7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:09:39.058580Z"},"content_sha256":"f099e6c1f69aebe75e8f31df82e2426741e79f01bc509aa9cca6d8065837c9c0","schema_version":"1.0","event_id":"sha256:f099e6c1f69aebe75e8f31df82e2426741e79f01bc509aa9cca6d8065837c9c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/bundle.json","state_url":"https://pith.science/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/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":"2026-08-18T12:09:39Z","links":{"resolver":"https://pith.science/pith/RLAY6RIYUA3K7NBATOUYUOSCWG","bundle":"https://pith.science/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/bundle.json","state":"https://pith.science/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLAY6RIYUA3K7NBATOUYUOSCWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RLAY6RIYUA3K7NBATOUYUOSCWG","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":"c51a3a6bc861359bd77db762791cf7b3a4eeacf8f7629c9ad33727b8d993452f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T16:19:00Z","title_canon_sha256":"6159a26d526e3663654fc59cf6234798e97b44e376a13d4328b23627ae2f098e"},"schema_version":"1.0","source":{"id":"2007.06028","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06028","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06028v3","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06028","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"RLAY6RIYUA3K","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"RLAY6RIYUA3K7NBA","created_at":"2026-07-05T03:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"RLAY6RIY","created_at":"2026-07-05T03:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:f099e6c1f69aebe75e8f31df82e2426741e79f01bc509aa9cca6d8065837c9c0","target":"graph","created_at":"2026-07-05T03:03:05Z","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/2007.06028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction, autoregressive prediction, or masked reconstruction. Unlike previous methods, we use alteration along three orthogonal axes to pre-train Transformer Encoders on a large amount of unlabeled speech. The model learns through the reconstruction of acoustic frames from their altered counterpart, where we use a stochastic policy to alter along various dimensions: time, f","authors_text":"Andy T. Liu, Hung-yi Lee, Shang-Wen Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T16:19:00Z","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06028","kind":"arxiv","version":3},"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":"sha256:8f80b3d302f099c89df0b398ae7e1fad603aa79c72d96fb5a8245e036de5ecad","target":"record","created_at":"2026-07-05T03:03:05Z","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":"c51a3a6bc861359bd77db762791cf7b3a4eeacf8f7629c9ad33727b8d993452f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-07-12T16:19:00Z","title_canon_sha256":"6159a26d526e3663654fc59cf6234798e97b44e376a13d4328b23627ae2f098e"},"schema_version":"1.0","source":{"id":"2007.06028","kind":"arxiv","version":3}},"canonical_sha256":"8ac18f4518a036afb4209ba98a3a42b1b141285e7714c6a3473c2d30bd6059f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac18f4518a036afb4209ba98a3a42b1b141285e7714c6a3473c2d30bd6059f0","first_computed_at":"2026-07-05T03:03:05.958156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:05.958156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DZuE3z0XrhEuq6ns7b1KwOF9gC5PA4K33ReuCK22JEiqeKROqca4kQvOXe2aqn8VQum+F8rZ9y16RXHCz/mNAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:05.958633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06028","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f80b3d302f099c89df0b398ae7e1fad603aa79c72d96fb5a8245e036de5ecad","sha256:f099e6c1f69aebe75e8f31df82e2426741e79f01bc509aa9cca6d8065837c9c0"],"state_sha256":"b3f0a7e7bafb53ab371a20e30e75fb95a3cc3e73db6b4820b560ea9dc74250c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZReXDG7dVwBfeQ0C5P6bWpqVGPC9kKeKjfN3rYOrAgINWVLfzTNFr/jfOFN/Q470357CaCjxCcf4XFKj6fkAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:09:39.063648Z","bundle_sha256":"a9e796f07e2d708936650fa47a2d34ecbc075e22486a0a6774e22e39bd553ac0"}}