{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LFYOHZACW7IXLCAEHVTJTQJ7LG","short_pith_number":"pith:LFYOHZAC","canonical_record":{"source":{"id":"1805.00545","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-01T20:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"ccb2f2d39e7c76d07cbdfbc5b0bb4040eaa4eb0471e31b090db1cc3c95cc7523","abstract_canon_sha256":"38d17295b6b015838116922f48cc75579939f10073bfff698ee0e4219e2f6c4f"},"schema_version":"1.0"},"canonical_sha256":"5970e3e402b7d17588043d6699c13f59bd53f9d9465b149db5dd58dc84a2c98f","source":{"kind":"arxiv","id":"1805.00545","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00545","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00545v1","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00545","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"LFYOHZACW7IX","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LFYOHZACW7IXLCAE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LFYOHZAC","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LFYOHZACW7IXLCAEHVTJTQJ7LG","target":"record","payload":{"canonical_record":{"source":{"id":"1805.00545","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-01T20:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"ccb2f2d39e7c76d07cbdfbc5b0bb4040eaa4eb0471e31b090db1cc3c95cc7523","abstract_canon_sha256":"38d17295b6b015838116922f48cc75579939f10073bfff698ee0e4219e2f6c4f"},"schema_version":"1.0"},"canonical_sha256":"5970e3e402b7d17588043d6699c13f59bd53f9d9465b149db5dd58dc84a2c98f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:58.585946Z","signature_b64":"wgtkqR15NXV7aYBVlorlibYERqTZ9e9juxSfoxLeaEQexhgrLcJRFnIHmNQO6H0D13aourXm8eUHmQEUDZMPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5970e3e402b7d17588043d6699c13f59bd53f9d9465b149db5dd58dc84a2c98f","last_reissued_at":"2026-05-18T00:16:58.585234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:58.585234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.00545","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":"2026-05-18T00:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34GFj3DmNReqEp/T+clAP0QdK5WSx3zYof7jeM6t2QiNhOAkN8xonfW2fE04OezG0wzBD3aC97LdTdIQ8Jp9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:14:39.247951Z"},"content_sha256":"8c1f8e317529efcd5984ed2acd980fe4494a4409c2b4c95c37ee9473712e09c4","schema_version":"1.0","event_id":"sha256:8c1f8e317529efcd5984ed2acd980fe4494a4409c2b4c95c37ee9473712e09c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LFYOHZACW7IXLCAEHVTJTQJ7LG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly Supervised Attention Learning for Textual Phrases Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shu Kong, Tianshu Yu, Yezhou Yang, Zhiyuan Fang","submitted_at":"2018-05-01T20:34:37Z","abstract_excerpt":"Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the supervised learning mechanism which requires ground-truth at pixel level during training. However, fine-grained level ground-truth annotation is quite time-consuming and severely narrows the scope for more general applications. In this extended abstract, we explore methods to localize flexibly image regions from the top-down signal (in a form of one-hot label or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00545","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":"2026-05-18T00:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDHSxbhi9oZNLGNS+nAa2gi+PCesPnG8RGo8fqyinZKFtkLeq+rNaNLxldHxzZdvCfFE+9DcHcp+hgnMcKzSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:14:39.248551Z"},"content_sha256":"49fa54d85da0a83ada297f56b802a024446e16489c910863c50263db4fee70a9","schema_version":"1.0","event_id":"sha256:49fa54d85da0a83ada297f56b802a024446e16489c910863c50263db4fee70a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/bundle.json","state_url":"https://pith.science/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/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":"2026-05-30T23:14:39Z","links":{"resolver":"https://pith.science/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG","bundle":"https://pith.science/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/bundle.json","state":"https://pith.science/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFYOHZACW7IXLCAEHVTJTQJ7LG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LFYOHZACW7IXLCAEHVTJTQJ7LG","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":"38d17295b6b015838116922f48cc75579939f10073bfff698ee0e4219e2f6c4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-01T20:34:37Z","title_canon_sha256":"ccb2f2d39e7c76d07cbdfbc5b0bb4040eaa4eb0471e31b090db1cc3c95cc7523"},"schema_version":"1.0","source":{"id":"1805.00545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00545","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00545v1","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00545","created_at":"2026-05-18T00:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"LFYOHZACW7IX","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LFYOHZACW7IXLCAE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LFYOHZAC","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:49fa54d85da0a83ada297f56b802a024446e16489c910863c50263db4fee70a9","target":"graph","created_at":"2026-05-18T00:16:58Z","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":"Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the supervised learning mechanism which requires ground-truth at pixel level during training. However, fine-grained level ground-truth annotation is quite time-consuming and severely narrows the scope for more general applications. In this extended abstract, we explore methods to localize flexibly image regions from the top-down signal (in a form of one-hot label or ","authors_text":"Shu Kong, Tianshu Yu, Yezhou Yang, Zhiyuan Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-01T20:34:37Z","title":"Weakly Supervised Attention Learning for Textual Phrases Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00545","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":"sha256:8c1f8e317529efcd5984ed2acd980fe4494a4409c2b4c95c37ee9473712e09c4","target":"record","created_at":"2026-05-18T00:16:58Z","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":"38d17295b6b015838116922f48cc75579939f10073bfff698ee0e4219e2f6c4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-01T20:34:37Z","title_canon_sha256":"ccb2f2d39e7c76d07cbdfbc5b0bb4040eaa4eb0471e31b090db1cc3c95cc7523"},"schema_version":"1.0","source":{"id":"1805.00545","kind":"arxiv","version":1}},"canonical_sha256":"5970e3e402b7d17588043d6699c13f59bd53f9d9465b149db5dd58dc84a2c98f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5970e3e402b7d17588043d6699c13f59bd53f9d9465b149db5dd58dc84a2c98f","first_computed_at":"2026-05-18T00:16:58.585234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:58.585234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wgtkqR15NXV7aYBVlorlibYERqTZ9e9juxSfoxLeaEQexhgrLcJRFnIHmNQO6H0D13aourXm8eUHmQEUDZMPAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:58.585946Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.00545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c1f8e317529efcd5984ed2acd980fe4494a4409c2b4c95c37ee9473712e09c4","sha256:49fa54d85da0a83ada297f56b802a024446e16489c910863c50263db4fee70a9"],"state_sha256":"48518446ea9561a7245fe2b74c8a6fd0995fa4e78e9750f9fd50064b34372d71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z+12jqwBOuB2xnGML4FvmMvlM9tJxv256cbi3xRxmLQR25yMmy4UypWy3vZN1qtWFh0RCwxiIsu48B4YABYEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:14:39.251490Z","bundle_sha256":"88fa90ddd8f6189b8944b8f86d70a1f26083a085c5c6c52d5fb1e1e1ab781e87"}}