{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LUISWY4KLXE63QPVITRLUJYLC4","short_pith_number":"pith:LUISWY4K","canonical_record":{"source":{"id":"1704.07434","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"576757be070b50a8c5330e32d35c888c0d495bfd312d58b1968eceee4f1bbde5","abstract_canon_sha256":"31a196a689bab7e31f3ae0169359c30029c3efdd64bf2edf049bd0ef1ebbd682"},"schema_version":"1.0"},"canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","source":{"kind":"arxiv","id":"1704.07434","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.07434","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"1704.07434v3","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07434","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"LUISWY4KLXE6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LUISWY4KLXE63QPV","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LUISWY4K","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LUISWY4KLXE63QPVITRLUJYLC4","target":"record","payload":{"canonical_record":{"source":{"id":"1704.07434","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"576757be070b50a8c5330e32d35c888c0d495bfd312d58b1968eceee4f1bbde5","abstract_canon_sha256":"31a196a689bab7e31f3ae0169359c30029c3efdd64bf2edf049bd0ef1ebbd682"},"schema_version":"1.0"},"canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:39.662329Z","signature_b64":"FOT5FsAfvaQQU/+Fd9zmu0dBPgc5OMZlzTi/PkuowuEstqJ7iN3pUtRsnVTOyYOQwwtv83QifnyMI94pXc/yCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","last_reissued_at":"2026-05-18T00:38:39.661777Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:39.661777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.07434","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZNS2UzsdnyWBQ53Urm78HLPekb1tLCBNAkESUKB2Y6S2XOaV7FrlLkW7oU5jH8hkMvQDy7uZ0XGvK4FpcbbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:05:23.133281Z"},"content_sha256":"2abf730932724066890394269eaebc920aeb25c3278fb7982d7a96e2a4057fa5","schema_version":"1.0","event_id":"sha256:2abf730932724066890394269eaebc920aeb25c3278fb7982d7a96e2a4057fa5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LUISWY4KLXE63QPVITRLUJYLC4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Paying Attention to Descriptions Generated by Image Captioning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ali Borji, Hamed R. Tavakoli, Jorma Laaksonen, Rakshith Shetty","submitted_at":"2017-04-24T19:51:16Z","abstract_excerpt":"To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07434","kind":"arxiv","version":3},"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":"2026-05-18T00:38:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zLa3ipWVDw6/j2NF5XTu0eADF0PQTAheRR83jhCccPYDlfl1jR9kif83reRQOwi6s4STCEkb9BbZEMpEUx29AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:05:23.133650Z"},"content_sha256":"3260abd7d4e630dc4edf5e5b36ff471029519c28fc4b3fc987607f11f9067ed0","schema_version":"1.0","event_id":"sha256:3260abd7d4e630dc4edf5e5b36ff471029519c28fc4b3fc987607f11f9067ed0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/bundle.json","state_url":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUISWY4KLXE63QPVITRLUJYLC4/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":"2026-06-05T10:05:23Z","links":{"resolver":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4","bundle":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/bundle.json","state":"https://pith.science/pith/LUISWY4KLXE63QPVITRLUJYLC4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUISWY4KLXE63QPVITRLUJYLC4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LUISWY4KLXE63QPVITRLUJYLC4","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":"31a196a689bab7e31f3ae0169359c30029c3efdd64bf2edf049bd0ef1ebbd682","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","title_canon_sha256":"576757be070b50a8c5330e32d35c888c0d495bfd312d58b1968eceee4f1bbde5"},"schema_version":"1.0","source":{"id":"1704.07434","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.07434","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"1704.07434v3","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07434","created_at":"2026-05-18T00:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"LUISWY4KLXE6","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LUISWY4KLXE63QPV","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LUISWY4K","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:3260abd7d4e630dc4edf5e5b36ff471029519c28fc4b3fc987607f11f9067ed0","target":"graph","created_at":"2026-05-18T00:38:39Z","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":"To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i","authors_text":"Ali Borji, Hamed R. Tavakoli, Jorma Laaksonen, Rakshith Shetty","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","title":"Paying Attention to Descriptions Generated by Image Captioning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07434","kind":"arxiv","version":3},"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":"sha256:2abf730932724066890394269eaebc920aeb25c3278fb7982d7a96e2a4057fa5","target":"record","created_at":"2026-05-18T00:38:39Z","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":"31a196a689bab7e31f3ae0169359c30029c3efdd64bf2edf049bd0ef1ebbd682","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-24T19:51:16Z","title_canon_sha256":"576757be070b50a8c5330e32d35c888c0d495bfd312d58b1968eceee4f1bbde5"},"schema_version":"1.0","source":{"id":"1704.07434","kind":"arxiv","version":3}},"canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d112b638a5dc9edc1f544e2ba270b1711c7636709b8761794401e85ed2dc078","first_computed_at":"2026-05-18T00:38:39.661777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:39.661777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FOT5FsAfvaQQU/+Fd9zmu0dBPgc5OMZlzTi/PkuowuEstqJ7iN3pUtRsnVTOyYOQwwtv83QifnyMI94pXc/yCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:39.662329Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.07434","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2abf730932724066890394269eaebc920aeb25c3278fb7982d7a96e2a4057fa5","sha256:3260abd7d4e630dc4edf5e5b36ff471029519c28fc4b3fc987607f11f9067ed0"],"state_sha256":"20e126365fe973476518d9100cc4177581fdebf07480ebea26195e2b0f8f16b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oARgggfF+2ozOGKeuy/wtdS6ixiIFKZLhYS+gL6LTTV9xq0GtbwkzvX4ytdT63OKqXqGYB+3g18SqLCAnprIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T10:05:23.135760Z","bundle_sha256":"76a58011934416dff121f447f99f696fe62fa2c9cbe573222db865bfd3b4be36"}}