{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OKM6BLN6ZVSVOLZLNYCZX2QJJQ","short_pith_number":"pith:OKM6BLN6","canonical_record":{"source":{"id":"2108.01056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T17:28:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6bc9193048e3a37982bfbf0ddae18c43d1b6b8b7c1a49228a35457a7639aa019","abstract_canon_sha256":"5c969530a337bb4c40e3d042fa65e8addb1fba83cfb74dc1a4f1eaa5abc5f62b"},"schema_version":"1.0"},"canonical_sha256":"7299e0adbecd65572f2b6e059bea094c120b7bf8a0e7d8883a5a9c0e55d763ac","source":{"kind":"arxiv","id":"2108.01056","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01056","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01056v2","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01056","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"OKM6BLN6ZVSV","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"OKM6BLN6ZVSVOLZL","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"OKM6BLN6","created_at":"2026-07-05T03:07:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OKM6BLN6ZVSVOLZLNYCZX2QJJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2108.01056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T17:28:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6bc9193048e3a37982bfbf0ddae18c43d1b6b8b7c1a49228a35457a7639aa019","abstract_canon_sha256":"5c969530a337bb4c40e3d042fa65e8addb1fba83cfb74dc1a4f1eaa5abc5f62b"},"schema_version":"1.0"},"canonical_sha256":"7299e0adbecd65572f2b6e059bea094c120b7bf8a0e7d8883a5a9c0e55d763ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:51.125368Z","signature_b64":"Kl68oXSlv8UdCRAJ5QI3IKwzomMZPP5QSUDHzJgpCfyjRt5oDRMc8mBRC3I6rkyK6vPO+E2jmC19z8pIjroOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7299e0adbecd65572f2b6e059bea094c120b7bf8a0e7d8883a5a9c0e55d763ac","last_reissued_at":"2026-07-05T03:07:51.124946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:51.124946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.01056","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:07:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bwQP++Eftg9BZTpMHnI0WWEPHVEADVDewfT1v+wv0EmlgJgZefyXHq7Rd2V6EHt3eh7PvGj17hHkk5PT4s4uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:59:46.893681Z"},"content_sha256":"80d3d44db15e23d0d16001ffe8086d7d9134eebc67401668800ae91e31cd3f69","schema_version":"1.0","event_id":"sha256:80d3d44db15e23d0d16001ffe8086d7d9134eebc67401668800ae91e31cd3f69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OKM6BLN6ZVSVOLZLNYCZX2QJJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Attention for Grounded Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Feiyue Huang, Haolei Yuan, Lei Yang, Nenglun Chen, Runnan Chen, Wenping Wang, Xiaowei Guo, Xingjia Pan, Yuqiang Ren, Zhiwen Lin","submitted_at":"2021-08-02T17:28:33Z","abstract_excerpt":"We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in the image. This task is challenging due to the lack of explicit fine-grained region word alignments as supervision. Previous weakly supervised methods mainly explore various kinds of regularization schemes to improve attention accuracy. However, their performances are still far from the fully supervised ones. One main issue that has been ignored is that the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01056","kind":"arxiv","version":2},"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/2108.01056/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":"2026-07-05T03:07:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZi9/kI85kyaH8RDNw+ePLnG3pAgcMnmx1odi00YChyIzohGOsz8nbDlPdTHYRyvXgGF7PqD+hm7TdTc8yVGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:59:46.894613Z"},"content_sha256":"a2356c0f0ed8f633784bf608ca61b908ca3c5e2515a25d58f9cefb22b98c8dc9","schema_version":"1.0","event_id":"sha256:a2356c0f0ed8f633784bf608ca61b908ca3c5e2515a25d58f9cefb22b98c8dc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/bundle.json","state_url":"https://pith.science/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/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":"2026-08-22T19:59:46Z","links":{"resolver":"https://pith.science/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ","bundle":"https://pith.science/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/bundle.json","state":"https://pith.science/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKM6BLN6ZVSVOLZLNYCZX2QJJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OKM6BLN6ZVSVOLZLNYCZX2QJJQ","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":"5c969530a337bb4c40e3d042fa65e8addb1fba83cfb74dc1a4f1eaa5abc5f62b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T17:28:33Z","title_canon_sha256":"6bc9193048e3a37982bfbf0ddae18c43d1b6b8b7c1a49228a35457a7639aa019"},"schema_version":"1.0","source":{"id":"2108.01056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01056","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01056v2","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01056","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"OKM6BLN6ZVSV","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"OKM6BLN6ZVSVOLZL","created_at":"2026-07-05T03:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"OKM6BLN6","created_at":"2026-07-05T03:07:51Z"}],"graph_snapshots":[{"event_id":"sha256:a2356c0f0ed8f633784bf608ca61b908ca3c5e2515a25d58f9cefb22b98c8dc9","target":"graph","created_at":"2026-07-05T03:07:51Z","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/2108.01056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in the image. This task is challenging due to the lack of explicit fine-grained region word alignments as supervision. Previous weakly supervised methods mainly explore various kinds of regularization schemes to improve attention accuracy. However, their performances are still far from the fully supervised ones. One main issue that has been ignored is that the a","authors_text":"Feiyue Huang, Haolei Yuan, Lei Yang, Nenglun Chen, Runnan Chen, Wenping Wang, Xiaowei Guo, Xingjia Pan, Yuqiang Ren, Zhiwen Lin","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T17:28:33Z","title":"Distributed Attention for Grounded Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01056","kind":"arxiv","version":2},"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":"sha256:80d3d44db15e23d0d16001ffe8086d7d9134eebc67401668800ae91e31cd3f69","target":"record","created_at":"2026-07-05T03:07:51Z","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":"5c969530a337bb4c40e3d042fa65e8addb1fba83cfb74dc1a4f1eaa5abc5f62b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T17:28:33Z","title_canon_sha256":"6bc9193048e3a37982bfbf0ddae18c43d1b6b8b7c1a49228a35457a7639aa019"},"schema_version":"1.0","source":{"id":"2108.01056","kind":"arxiv","version":2}},"canonical_sha256":"7299e0adbecd65572f2b6e059bea094c120b7bf8a0e7d8883a5a9c0e55d763ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7299e0adbecd65572f2b6e059bea094c120b7bf8a0e7d8883a5a9c0e55d763ac","first_computed_at":"2026-07-05T03:07:51.124946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:51.124946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kl68oXSlv8UdCRAJ5QI3IKwzomMZPP5QSUDHzJgpCfyjRt5oDRMc8mBRC3I6rkyK6vPO+E2jmC19z8pIjroOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:51.125368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d3d44db15e23d0d16001ffe8086d7d9134eebc67401668800ae91e31cd3f69","sha256:a2356c0f0ed8f633784bf608ca61b908ca3c5e2515a25d58f9cefb22b98c8dc9"],"state_sha256":"f3f219064c7599118c749b86fe94d7b85c6b5ebf7ca06f78f0850d49a49bcfd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYX8Gmi7GVW33a0EhQr3qBert5yKhuxu1rxhsvoGcWnNW0o3GKjwIMMdmDzsHk4aSPb2o3h61AynyFw3/w8aBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T19:59:46.900575Z","bundle_sha256":"f28f0b894557a6cf9917223267ccc6c70e990305dbff0ab31c8307893e6d1d38"}}