{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7B2553RIRI3UJ7VSPZOIY7WLK5","short_pith_number":"pith:7B2553RI","canonical_record":{"source":{"id":"1812.11004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"3b071ae608ff751cfe3b81a8224b33b11e04eafad500dcbb0af5683fae697aba","abstract_canon_sha256":"f31bcd5a32d11c217015d57daeff83be2fa4949d4dd4521933568270f6192115"},"schema_version":"1.0"},"canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","source":{"kind":"arxiv","id":"1812.11004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11004","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11004v1","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11004","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"pith_short_12","alias_value":"7B2553RIRI3U","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7B2553RIRI3UJ7VS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7B2553RI","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7B2553RIRI3UJ7VSPZOIY7WLK5","target":"record","payload":{"canonical_record":{"source":{"id":"1812.11004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"3b071ae608ff751cfe3b81a8224b33b11e04eafad500dcbb0af5683fae697aba","abstract_canon_sha256":"f31bcd5a32d11c217015d57daeff83be2fa4949d4dd4521933568270f6192115"},"schema_version":"1.0"},"canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:16.583186Z","signature_b64":"Hnd3zr7bZeQfRWkDSDldozp2/zZNPhQ4r4ZBpW5RNuXCqzij/VXSWr4lgPel27NuwqRIuA45a5Wp48PNIclwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","last_reissued_at":"2026-05-17T23:57:16.582748Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:16.582748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.11004","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":"2026-05-17T23:57:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYcOExdE23xqesBYUVGTecwqdRBxNrSosIIXk8r936q+2z1AvlAfT/ozMxVAMvzhV50vHn2rYoEIzDyjEShPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:57:29.984840Z"},"content_sha256":"5ec4763768623623318ded5a4b86706a53744d11b0ecf0a60b3875902bc213b4","schema_version":"1.0","event_id":"sha256:5ec4763768623623318ded5a4b86706a53744d11b0ecf0a60b3875902bc213b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7B2553RIRI3UJ7VSPZOIY7WLK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Tao Shen, Jingkuan Song, Lianli Gao, Xiangpeng Li","submitted_at":"2018-12-26T09:51:58Z","abstract_excerpt":"Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11004","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":""},"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":"2026-05-17T23:57:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUZWarGuwtf5C9WrsJ4PmmT5qOGoxlHe6sA2CL2JzWqxaw/fxLw9SBrmJc/6DdDoX5xjcgFQI2j0lxt7pHG/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:57:29.985205Z"},"content_sha256":"8d6ecf30c0ff12c4d7f9836126e9d60bba29bf48ddc46391f99834444d802090","schema_version":"1.0","event_id":"sha256:8d6ecf30c0ff12c4d7f9836126e9d60bba29bf48ddc46391f99834444d802090"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/bundle.json","state_url":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/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":"2026-05-31T06:57:29Z","links":{"resolver":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5","bundle":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/bundle.json","state":"https://pith.science/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7B2553RIRI3UJ7VSPZOIY7WLK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7B2553RIRI3UJ7VSPZOIY7WLK5","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":"f31bcd5a32d11c217015d57daeff83be2fa4949d4dd4521933568270f6192115","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","title_canon_sha256":"3b071ae608ff751cfe3b81a8224b33b11e04eafad500dcbb0af5683fae697aba"},"schema_version":"1.0","source":{"id":"1812.11004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11004","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11004v1","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11004","created_at":"2026-05-17T23:57:16Z"},{"alias_kind":"pith_short_12","alias_value":"7B2553RIRI3U","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7B2553RIRI3UJ7VS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7B2553RI","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:8d6ecf30c0ff12c4d7f9836126e9d60bba29bf48ddc46391f99834444d802090","target":"graph","created_at":"2026-05-17T23:57:16Z","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"},"paper":{"abstract_excerpt":"Recent progress has been made in using attention based encoder-decoder framework for image and video captioning. Most existing decoders apply the attention mechanism to every generated word including both visual words (e.g., \"gun\" and \"shooting\") and non-visual words (e.g. \"the\", \"a\"). However, these non-visual words can be easily predicted using natural language model without considering visual signals or attention. Imposing attention mechanism on non-visual words could mislead and decrease the overall performance of visual captioning. Furthermore, the hierarchy of LSTMs enables more complex ","authors_text":"Heng Tao Shen, Jingkuan Song, Lianli Gao, Xiangpeng Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11004","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":"sha256:5ec4763768623623318ded5a4b86706a53744d11b0ecf0a60b3875902bc213b4","target":"record","created_at":"2026-05-17T23:57:16Z","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":"f31bcd5a32d11c217015d57daeff83be2fa4949d4dd4521933568270f6192115","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-26T09:51:58Z","title_canon_sha256":"3b071ae608ff751cfe3b81a8224b33b11e04eafad500dcbb0af5683fae697aba"},"schema_version":"1.0","source":{"id":"1812.11004","kind":"arxiv","version":1}},"canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f875deee288a3744feb27e5c8c7ecb5758854e36d75e5ff086b4b2b3527e5491","first_computed_at":"2026-05-17T23:57:16.582748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:16.582748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hnd3zr7bZeQfRWkDSDldozp2/zZNPhQ4r4ZBpW5RNuXCqzij/VXSWr4lgPel27NuwqRIuA45a5Wp48PNIclwBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:16.583186Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.11004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ec4763768623623318ded5a4b86706a53744d11b0ecf0a60b3875902bc213b4","sha256:8d6ecf30c0ff12c4d7f9836126e9d60bba29bf48ddc46391f99834444d802090"],"state_sha256":"349292fe684402b8dad08e7cd227694c8ce3c4846fe99d25938fc8d4bc4522f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybtBIKpYxuG/JwBtyysuInOQOW5PZMHydrHTHXH+sp3NkzWggR11QcxgmGuIdM9ofiITYuBPXUXeHjngKeiWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:57:29.987623Z","bundle_sha256":"8d1964f2921214ed98df865f1f255f4356e6498a9d19703cf0f8c03114ef3d7c"}}