{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UEZ3DKVZMOCZ6LGZFPNSDIMI3V","short_pith_number":"pith:UEZ3DKVZ","canonical_record":{"source":{"id":"2101.11562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-27T17:36:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ce0215a62ab3c6edca10dec2cd4b8b42847fb37296fb0b888eee33a95e8bf01c","abstract_canon_sha256":"a21d0081dd70396574f62f6bae08b704ff2565ddd5c3bbaf94065508d76c738d"},"schema_version":"1.0"},"canonical_sha256":"a133b1aab963859f2cd92bdb21a188dd71c2d246f9e16ec6ecc16bb057719361","source":{"kind":"arxiv","id":"2101.11562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11562","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11562v1","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11562","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"UEZ3DKVZMOCZ","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"UEZ3DKVZMOCZ6LGZ","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"UEZ3DKVZ","created_at":"2026-07-05T02:10:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UEZ3DKVZMOCZ6LGZFPNSDIMI3V","target":"record","payload":{"canonical_record":{"source":{"id":"2101.11562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-27T17:36:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ce0215a62ab3c6edca10dec2cd4b8b42847fb37296fb0b888eee33a95e8bf01c","abstract_canon_sha256":"a21d0081dd70396574f62f6bae08b704ff2565ddd5c3bbaf94065508d76c738d"},"schema_version":"1.0"},"canonical_sha256":"a133b1aab963859f2cd92bdb21a188dd71c2d246f9e16ec6ecc16bb057719361","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:21.218026Z","signature_b64":"qrbk8wpAbmZpVz2y+zC38DPPj5AjKcxJpfDJMpSj53JZailGVNLWj44lQFl8AssMCF1ToYn802rLsXA5HgPoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a133b1aab963859f2cd92bdb21a188dd71c2d246f9e16ec6ecc16bb057719361","last_reissued_at":"2026-07-05T02:10:21.217642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:21.217642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.11562","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":"2026-07-05T02:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qYQBR20Z5LYwLUds7KMUP6nHles4KHjgzj/ydFuN43oZdi9Kq+61na1TWrEZhcpWgM9w6C11sfLuwLOjSHlAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:12.537720Z"},"content_sha256":"03c1090b8d310ffc73180868d445ce53d45c884f6aaaba76d0f7a0c01269f947","schema_version":"1.0","event_id":"sha256:03c1090b8d310ffc73180868d445ce53d45c884f6aaaba76d0f7a0c01269f947"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UEZ3DKVZMOCZ6LGZFPNSDIMI3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jingwen Chen, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2021-01-27T17:36:57Z","abstract_excerpt":"Despite having impressive vision-language (VL) pretraining with BERT-based encoder for VL understanding, the pretraining of a universal encoder-decoder for both VL understanding and generation remains challenging. The difficulty originates from the inherently different peculiarities of the two disciplines, e.g., VL understanding tasks capitalize on the unrestricted message passing across modalities, while generation tasks only employ visual-to-textual message passing. In this paper, we start with a two-stream decoupled design of encoder-decoder structure, in which two decoupled cross-modal enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11562","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/2101.11562/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":"2026-07-05T02:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obk0k2CBYEQmT8wjZOT8A4+J3eE7IUJLRrMFAlR8zsR4Zi4BJkCpbLuxSJgS1Mte+EcqyywuD0DJWBz1zM22CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:12.538279Z"},"content_sha256":"866d0ddfa31f5aeebe90a56868bec26f972a45cfcfaad09caa7afb7402851d0f","schema_version":"1.0","event_id":"sha256:866d0ddfa31f5aeebe90a56868bec26f972a45cfcfaad09caa7afb7402851d0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/bundle.json","state_url":"https://pith.science/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/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":"2026-08-07T01:45:12Z","links":{"resolver":"https://pith.science/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V","bundle":"https://pith.science/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/bundle.json","state":"https://pith.science/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UEZ3DKVZMOCZ6LGZFPNSDIMI3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UEZ3DKVZMOCZ6LGZFPNSDIMI3V","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":"a21d0081dd70396574f62f6bae08b704ff2565ddd5c3bbaf94065508d76c738d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-27T17:36:57Z","title_canon_sha256":"ce0215a62ab3c6edca10dec2cd4b8b42847fb37296fb0b888eee33a95e8bf01c"},"schema_version":"1.0","source":{"id":"2101.11562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11562","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11562v1","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11562","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"UEZ3DKVZMOCZ","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"UEZ3DKVZMOCZ6LGZ","created_at":"2026-07-05T02:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"UEZ3DKVZ","created_at":"2026-07-05T02:10:21Z"}],"graph_snapshots":[{"event_id":"sha256:866d0ddfa31f5aeebe90a56868bec26f972a45cfcfaad09caa7afb7402851d0f","target":"graph","created_at":"2026-07-05T02:10:21Z","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/2101.11562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite having impressive vision-language (VL) pretraining with BERT-based encoder for VL understanding, the pretraining of a universal encoder-decoder for both VL understanding and generation remains challenging. The difficulty originates from the inherently different peculiarities of the two disciplines, e.g., VL understanding tasks capitalize on the unrestricted message passing across modalities, while generation tasks only employ visual-to-textual message passing. In this paper, we start with a two-stream decoupled design of encoder-decoder structure, in which two decoupled cross-modal enc","authors_text":"Jingwen Chen, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-27T17:36:57Z","title":"Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11562","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":"sha256:03c1090b8d310ffc73180868d445ce53d45c884f6aaaba76d0f7a0c01269f947","target":"record","created_at":"2026-07-05T02:10:21Z","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":"a21d0081dd70396574f62f6bae08b704ff2565ddd5c3bbaf94065508d76c738d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-27T17:36:57Z","title_canon_sha256":"ce0215a62ab3c6edca10dec2cd4b8b42847fb37296fb0b888eee33a95e8bf01c"},"schema_version":"1.0","source":{"id":"2101.11562","kind":"arxiv","version":1}},"canonical_sha256":"a133b1aab963859f2cd92bdb21a188dd71c2d246f9e16ec6ecc16bb057719361","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a133b1aab963859f2cd92bdb21a188dd71c2d246f9e16ec6ecc16bb057719361","first_computed_at":"2026-07-05T02:10:21.217642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:21.217642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qrbk8wpAbmZpVz2y+zC38DPPj5AjKcxJpfDJMpSj53JZailGVNLWj44lQFl8AssMCF1ToYn802rLsXA5HgPoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:21.218026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.11562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03c1090b8d310ffc73180868d445ce53d45c884f6aaaba76d0f7a0c01269f947","sha256:866d0ddfa31f5aeebe90a56868bec26f972a45cfcfaad09caa7afb7402851d0f"],"state_sha256":"e466f87023b21a1bab310ba7f7818250ffb835f9e7642886b7999d292b801bcc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDGD5HNvNF+pOjPPpv8Ed8DHHVhQOYhhIOWsuGgt0idmTBLCTrOiM6o61VmEakLxq4Pc4jiC7K3JkO/LxHSACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:12.541874Z","bundle_sha256":"c798d91ef4bdad06f38fae1110784ac0db5f33129a66cd658b4c3260deae3a2a"}}