{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:W5JD3WBMR4VYH4ZBQH6TURTXPG","short_pith_number":"pith:W5JD3WBM","canonical_record":{"source":{"id":"1705.01371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T11:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"ea22eaf52bec1fab9ff1720c9ea728b21fe0a5672ab4b55714a8408d29e38a49","abstract_canon_sha256":"4b95da438371fbf10062a79066e51d4297ce4d8334bf55f8e31b85d4fcc9ad96"},"schema_version":"1.0"},"canonical_sha256":"b7523dd82c8f2b83f32181fd3a467779ade71950f582c8e0452420a59e8d20f2","source":{"kind":"arxiv","id":"1705.01371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01371","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01371v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01371","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"W5JD3WBMR4VY","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W5JD3WBMR4VYH4ZB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W5JD3WBM","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:W5JD3WBMR4VYH4ZBQH6TURTXPG","target":"record","payload":{"canonical_record":{"source":{"id":"1705.01371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T11:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"ea22eaf52bec1fab9ff1720c9ea728b21fe0a5672ab4b55714a8408d29e38a49","abstract_canon_sha256":"4b95da438371fbf10062a79066e51d4297ce4d8334bf55f8e31b85d4fcc9ad96"},"schema_version":"1.0"},"canonical_sha256":"b7523dd82c8f2b83f32181fd3a467779ade71950f582c8e0452420a59e8d20f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:05.308601Z","signature_b64":"n9ha5O39V1FEgv6fnxJ4V4L7Ec3KJs6bgT4oWsP5B/4rRPXdPk9C1dx7VTtf3WhxQyvI9c0k5NkRRE7J3w56BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7523dd82c8f2b83f32181fd3a467779ade71950f582c8e0452420a59e8d20f2","last_reissued_at":"2026-05-18T00:45:05.308200Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:05.308200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.01371","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qudhtRDnDcm3wT45kkKak0VYszlDReB8+tBKg0pAGIPr3fOjK+FwVpCxuoF3L5B+CXm7we3G0HA78K2fFWIwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:50:00.004452Z"},"content_sha256":"beca29b460727d22de601c22c6f772b69e15f52b104b4605f0a237116d12690a","schema_version":"1.0","event_id":"sha256:beca29b460727d22de601c22c6f772b69e15f52b104b4605f0a237116d12690a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:W5JD3WBMR4VYH4ZBQH6TURTXPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyi Xiao, Leonid Sigal, Yong Jae Lee","submitted_at":"2017-05-03T11:53:33Z","abstract_excerpt":"We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with images and their associated image-level captions, without any explicit region-to-phrase correspondence annotations. To this end, we introduce an end-to-end model which learns visual groundings of phrases with two types of carefully designed loss functions. In addition to the standard discriminative loss, which enforces that attended image regions and phrases a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01371","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"La0sEXU81qXCyDwUMivU15lt+//nADQODW4QIc8QXXYdWGK/QlTUSZZQTLHCAV7NF4FUPGq8UR/kkFk7OOB3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T05:50:00.004814Z"},"content_sha256":"debd073ec9d2c33340c18b1125821672dd2b808f71b5af312d57588808be6eca","schema_version":"1.0","event_id":"sha256:debd073ec9d2c33340c18b1125821672dd2b808f71b5af312d57588808be6eca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/bundle.json","state_url":"https://pith.science/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/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":"2026-05-28T05:50:00Z","links":{"resolver":"https://pith.science/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG","bundle":"https://pith.science/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/bundle.json","state":"https://pith.science/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5JD3WBMR4VYH4ZBQH6TURTXPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:W5JD3WBMR4VYH4ZBQH6TURTXPG","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":"4b95da438371fbf10062a79066e51d4297ce4d8334bf55f8e31b85d4fcc9ad96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T11:53:33Z","title_canon_sha256":"ea22eaf52bec1fab9ff1720c9ea728b21fe0a5672ab4b55714a8408d29e38a49"},"schema_version":"1.0","source":{"id":"1705.01371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01371","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01371v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01371","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"W5JD3WBMR4VY","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"W5JD3WBMR4VYH4ZB","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"W5JD3WBM","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:debd073ec9d2c33340c18b1125821672dd2b808f71b5af312d57588808be6eca","target":"graph","created_at":"2026-05-18T00:45:05Z","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":"We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with images and their associated image-level captions, without any explicit region-to-phrase correspondence annotations. To this end, we introduce an end-to-end model which learns visual groundings of phrases with two types of carefully designed loss functions. In addition to the standard discriminative loss, which enforces that attended image regions and phrases a","authors_text":"Fanyi Xiao, Leonid Sigal, Yong Jae Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T11:53:33Z","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01371","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:beca29b460727d22de601c22c6f772b69e15f52b104b4605f0a237116d12690a","target":"record","created_at":"2026-05-18T00:45:05Z","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":"4b95da438371fbf10062a79066e51d4297ce4d8334bf55f8e31b85d4fcc9ad96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-03T11:53:33Z","title_canon_sha256":"ea22eaf52bec1fab9ff1720c9ea728b21fe0a5672ab4b55714a8408d29e38a49"},"schema_version":"1.0","source":{"id":"1705.01371","kind":"arxiv","version":1}},"canonical_sha256":"b7523dd82c8f2b83f32181fd3a467779ade71950f582c8e0452420a59e8d20f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7523dd82c8f2b83f32181fd3a467779ade71950f582c8e0452420a59e8d20f2","first_computed_at":"2026-05-18T00:45:05.308200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:05.308200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9ha5O39V1FEgv6fnxJ4V4L7Ec3KJs6bgT4oWsP5B/4rRPXdPk9C1dx7VTtf3WhxQyvI9c0k5NkRRE7J3w56BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:05.308601Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.01371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beca29b460727d22de601c22c6f772b69e15f52b104b4605f0a237116d12690a","sha256:debd073ec9d2c33340c18b1125821672dd2b808f71b5af312d57588808be6eca"],"state_sha256":"7bf73fbb0510bd4fa727caebfbbd0e589ae81c210be6d453c7e196b050b8adc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFeUpQuqn6H/vP/kB0q6DJK++8abCA6ceKYobJYqvx1Mcr5Nd5ktOkQSxDFmo6sV2iaJRwSTaF6BMH2IuqCACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T05:50:00.006789Z","bundle_sha256":"0a60ca1c6a44d9b256dfa95ef76dbac47e79a4bb1962453aaaa9d5dab7216c62"}}