{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VXIOERIELEKA5GCVO7UPNRBSJU","short_pith_number":"pith:VXIOERIE","canonical_record":{"source":{"id":"2106.08571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T06:36:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bb640da33bdddc03bf51f78128a54ed1be0aead4bb01ab7d80d4d31b5d07fdee","abstract_canon_sha256":"50153bb5d78b376a2d53e5426bcef0234fa7d8b556fe5b291cf450d393997e98"},"schema_version":"1.0"},"canonical_sha256":"add0e2450459140e985577e8f6c4324d2dd54978e2b21a484a36d646631d6093","source":{"kind":"arxiv","id":"2106.08571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08571","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08571v1","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08571","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"VXIOERIELEKA","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"VXIOERIELEKA5GCV","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"VXIOERIE","created_at":"2026-07-05T02:49:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VXIOERIELEKA5GCVO7UPNRBSJU","target":"record","payload":{"canonical_record":{"source":{"id":"2106.08571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T06:36:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bb640da33bdddc03bf51f78128a54ed1be0aead4bb01ab7d80d4d31b5d07fdee","abstract_canon_sha256":"50153bb5d78b376a2d53e5426bcef0234fa7d8b556fe5b291cf450d393997e98"},"schema_version":"1.0"},"canonical_sha256":"add0e2450459140e985577e8f6c4324d2dd54978e2b21a484a36d646631d6093","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:59.449609Z","signature_b64":"7PW0gLBeNYKSzFZgrTMmGO82dweXkhtngs/Ot06eOex0nrU/w0gRlYQHssvze39M7zwl5ugyHo6Auc9vPtEFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"add0e2450459140e985577e8f6c4324d2dd54978e2b21a484a36d646631d6093","last_reissued_at":"2026-07-05T02:49:59.449133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:59.449133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.08571","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":"2026-07-05T02:49:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVUInkGKE52EWlNmf9VhFPOe55AzFpvkR9YspP1BCbOkxko/bdc25M+YQL6eu4iAMkd8cYm3IPeXuc64bkf0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:57:42.397514Z"},"content_sha256":"48b9fbf22112feb6faf835e654a68ae5ddccbefc9b1acbb86820af2ddf54aac9","schema_version":"1.0","event_id":"sha256:48b9fbf22112feb6faf835e654a68ae5ddccbefc9b1acbb86820af2ddf54aac9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VXIOERIELEKA5GCVO7UPNRBSJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Auto-regressive Variational Attention Models for Text Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haoli Bai, Irwin King, Jian Li, Michael Lyu, Xianghong Fang, Zenglin Xu","submitted_at":"2021-06-16T06:36:26Z","abstract_excerpt":"Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a long-standing problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08571","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/2106.08571/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":"2026-07-05T02:49:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Njt8mvqcVKmdHA23lDNla4iUdlJULOFzkpWPbtsemPamGl3Yq+Ed29oc+oWHBBcKAlgMpcueddgCIx9ltGQuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:57:42.398303Z"},"content_sha256":"8305376a5b9430256e8ec175e168678e86200916f744b56935ba979dbf73f1ef","schema_version":"1.0","event_id":"sha256:8305376a5b9430256e8ec175e168678e86200916f744b56935ba979dbf73f1ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXIOERIELEKA5GCVO7UPNRBSJU/bundle.json","state_url":"https://pith.science/pith/VXIOERIELEKA5GCVO7UPNRBSJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXIOERIELEKA5GCVO7UPNRBSJU/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":"2026-07-07T02:57:42Z","links":{"resolver":"https://pith.science/pith/VXIOERIELEKA5GCVO7UPNRBSJU","bundle":"https://pith.science/pith/VXIOERIELEKA5GCVO7UPNRBSJU/bundle.json","state":"https://pith.science/pith/VXIOERIELEKA5GCVO7UPNRBSJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXIOERIELEKA5GCVO7UPNRBSJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VXIOERIELEKA5GCVO7UPNRBSJU","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":"50153bb5d78b376a2d53e5426bcef0234fa7d8b556fe5b291cf450d393997e98","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T06:36:26Z","title_canon_sha256":"bb640da33bdddc03bf51f78128a54ed1be0aead4bb01ab7d80d4d31b5d07fdee"},"schema_version":"1.0","source":{"id":"2106.08571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08571","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08571v1","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08571","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"VXIOERIELEKA","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"VXIOERIELEKA5GCV","created_at":"2026-07-05T02:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"VXIOERIE","created_at":"2026-07-05T02:49:59Z"}],"graph_snapshots":[{"event_id":"sha256:8305376a5b9430256e8ec175e168678e86200916f744b56935ba979dbf73f1ef","target":"graph","created_at":"2026-07-05T02:49:59Z","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/2106.08571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a long-standing problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifical","authors_text":"Haoli Bai, Irwin King, Jian Li, Michael Lyu, Xianghong Fang, Zenglin Xu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T06:36:26Z","title":"Discrete Auto-regressive Variational Attention Models for Text Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08571","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":"sha256:48b9fbf22112feb6faf835e654a68ae5ddccbefc9b1acbb86820af2ddf54aac9","target":"record","created_at":"2026-07-05T02:49:59Z","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":"50153bb5d78b376a2d53e5426bcef0234fa7d8b556fe5b291cf450d393997e98","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T06:36:26Z","title_canon_sha256":"bb640da33bdddc03bf51f78128a54ed1be0aead4bb01ab7d80d4d31b5d07fdee"},"schema_version":"1.0","source":{"id":"2106.08571","kind":"arxiv","version":1}},"canonical_sha256":"add0e2450459140e985577e8f6c4324d2dd54978e2b21a484a36d646631d6093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"add0e2450459140e985577e8f6c4324d2dd54978e2b21a484a36d646631d6093","first_computed_at":"2026-07-05T02:49:59.449133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:59.449133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7PW0gLBeNYKSzFZgrTMmGO82dweXkhtngs/Ot06eOex0nrU/w0gRlYQHssvze39M7zwl5ugyHo6Auc9vPtEFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:59.449609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48b9fbf22112feb6faf835e654a68ae5ddccbefc9b1acbb86820af2ddf54aac9","sha256:8305376a5b9430256e8ec175e168678e86200916f744b56935ba979dbf73f1ef"],"state_sha256":"c78e5b7b3e88eef5176872e7afa2ec30ebe7204f03800c1d65a22e44f9ef0e37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TdTpytyxVLw5m6yaMuV3k7vgYaW8zW8bA1itRO+gybZ9FK2XmNU+ZWbfaRUq2rWiCoUDJTgi5JK2NHMY48BAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:57:42.402223Z","bundle_sha256":"b647a96ad6932e2cca18dd190c46ca48fe5d9c0202dddc9c5333aa366076fbfb"}}