{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KAQ3MUPNLSX63MCKJCAQGKWE36","short_pith_number":"pith:KAQ3MUPN","canonical_record":{"source":{"id":"1701.03439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-12T18:03:52Z","cross_cats_sorted":[],"title_canon_sha256":"9c1fefb0bbf80ce4f83a237218baa81860605f0d2fef90af3f448416470f16fb","abstract_canon_sha256":"068227e93dc5bcc443e586bf1fa875cec5065ca02fe538f9242d371938918e54"},"schema_version":"1.0"},"canonical_sha256":"5021b651ed5cafedb04a4881032ac4df82544d27098587afc76a934cd5a319de","source":{"kind":"arxiv","id":"1701.03439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03439","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03439v1","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03439","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"KAQ3MUPNLSX6","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KAQ3MUPNLSX63MCK","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KAQ3MUPN","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KAQ3MUPNLSX63MCKJCAQGKWE36","target":"record","payload":{"canonical_record":{"source":{"id":"1701.03439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-12T18:03:52Z","cross_cats_sorted":[],"title_canon_sha256":"9c1fefb0bbf80ce4f83a237218baa81860605f0d2fef90af3f448416470f16fb","abstract_canon_sha256":"068227e93dc5bcc443e586bf1fa875cec5065ca02fe538f9242d371938918e54"},"schema_version":"1.0"},"canonical_sha256":"5021b651ed5cafedb04a4881032ac4df82544d27098587afc76a934cd5a319de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:55.864846Z","signature_b64":"DPvCigx8lUl3xOS3Kw2hY2UK3+4bP60xfHr4DxRPB9ifVHKQzKzwA5uHSwf0UanksfkFMJ6b+vjXDT+oFfnVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5021b651ed5cafedb04a4881032ac4df82544d27098587afc76a934cd5a319de","last_reissued_at":"2026-05-18T00:52:55.864133Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:55.864133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.03439","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":"2026-05-18T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGHnorhSjVIFqe/cgl6IMcM+sQqX8iPVX1Zi9+nPj/FmFWOUDnecW6URqsVB1rhsr2ShW4Y+xbcp0kOiCtZBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:36:22.956357Z"},"content_sha256":"fd0b592f8b60a203140ad2eee8ee5d67dd75db6418cf0d2f4152346febd00077","schema_version":"1.0","event_id":"sha256:fd0b592f8b60a203140ad2eee8ee5d67dd75db6418cf0d2f4152346febd00077"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KAQ3MUPNLSX63MCKJCAQGKWE36","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comprehension-guided referring expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gregory Shakhnarovich, Ruotian Luo","submitted_at":"2017-01-12T18:03:52Z","abstract_excerpt":"We consider generation and comprehension of natural language referring expression for objects in an image. Unlike generic \"image captioning\" which lacks natural standard evaluation criteria, quality of a referring expression may be measured by the receiver's ability to correctly infer which object is being described. Following this intuition, we propose two approaches to utilize models trained for comprehension task to generate better expressions. First, we use a comprehension module trained on human-generated expressions, as a \"critic\" of referring expression generator. The comprehension modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03439","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":"2026-05-18T00:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8awzeEgyuQgeFaGAF5S+ZpQUoFX5Fmenlo7XeVodz2ndGHS26mzWjvgcVLytrHM9vDFN/XOPERFOCU8gCT4ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:36:22.956977Z"},"content_sha256":"7af1daf7cc757adb6f5a54d96ee764a81849aa21ac94c5417d86ad7a7c0da9ec","schema_version":"1.0","event_id":"sha256:7af1daf7cc757adb6f5a54d96ee764a81849aa21ac94c5417d86ad7a7c0da9ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/bundle.json","state_url":"https://pith.science/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/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":"2026-05-31T07:36:22Z","links":{"resolver":"https://pith.science/pith/KAQ3MUPNLSX63MCKJCAQGKWE36","bundle":"https://pith.science/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/bundle.json","state":"https://pith.science/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAQ3MUPNLSX63MCKJCAQGKWE36/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KAQ3MUPNLSX63MCKJCAQGKWE36","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":"068227e93dc5bcc443e586bf1fa875cec5065ca02fe538f9242d371938918e54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-12T18:03:52Z","title_canon_sha256":"9c1fefb0bbf80ce4f83a237218baa81860605f0d2fef90af3f448416470f16fb"},"schema_version":"1.0","source":{"id":"1701.03439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03439","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03439v1","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03439","created_at":"2026-05-18T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"KAQ3MUPNLSX6","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KAQ3MUPNLSX63MCK","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KAQ3MUPN","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:7af1daf7cc757adb6f5a54d96ee764a81849aa21ac94c5417d86ad7a7c0da9ec","target":"graph","created_at":"2026-05-18T00:52:55Z","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 consider generation and comprehension of natural language referring expression for objects in an image. Unlike generic \"image captioning\" which lacks natural standard evaluation criteria, quality of a referring expression may be measured by the receiver's ability to correctly infer which object is being described. Following this intuition, we propose two approaches to utilize models trained for comprehension task to generate better expressions. First, we use a comprehension module trained on human-generated expressions, as a \"critic\" of referring expression generator. The comprehension modu","authors_text":"Gregory Shakhnarovich, Ruotian Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-12T18:03:52Z","title":"Comprehension-guided referring expressions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03439","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:fd0b592f8b60a203140ad2eee8ee5d67dd75db6418cf0d2f4152346febd00077","target":"record","created_at":"2026-05-18T00:52:55Z","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":"068227e93dc5bcc443e586bf1fa875cec5065ca02fe538f9242d371938918e54","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-12T18:03:52Z","title_canon_sha256":"9c1fefb0bbf80ce4f83a237218baa81860605f0d2fef90af3f448416470f16fb"},"schema_version":"1.0","source":{"id":"1701.03439","kind":"arxiv","version":1}},"canonical_sha256":"5021b651ed5cafedb04a4881032ac4df82544d27098587afc76a934cd5a319de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5021b651ed5cafedb04a4881032ac4df82544d27098587afc76a934cd5a319de","first_computed_at":"2026-05-18T00:52:55.864133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:55.864133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DPvCigx8lUl3xOS3Kw2hY2UK3+4bP60xfHr4DxRPB9ifVHKQzKzwA5uHSwf0UanksfkFMJ6b+vjXDT+oFfnVCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:55.864846Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.03439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd0b592f8b60a203140ad2eee8ee5d67dd75db6418cf0d2f4152346febd00077","sha256:7af1daf7cc757adb6f5a54d96ee764a81849aa21ac94c5417d86ad7a7c0da9ec"],"state_sha256":"7e8dfc8cc4e9eb5272db1f3d99d5c9b158e765dc324e4f0c5e81fe2ad0621bae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfBHeu2EZYoLcfmuzOsmuPoRP2CtPkBExkdQmBdNvUn8Kz3h3lC1UCTK5xutv8cBXI1eteVllWIgWXMKH/JGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:36:22.960016Z","bundle_sha256":"1b39fe9ba61207eca0bb4a7d3ab1eba12355dba69616405aec9306f8302c6a2e"}}