{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AVBWDD5TPAFTOUH2HDJHGKKAAH","short_pith_number":"pith:AVBWDD5T","schema_version":"1.0","canonical_sha256":"0543618fb3780b3750fa38d273294001f567c07e430573e5e2c5b0f52fd9c1ba","source":{"kind":"arxiv","id":"2105.05964","version":1},"attestation_state":"computed","paper":{"title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amy Bearman, Babak Damavandi, Licheng Yu, Ning Zhang, Tamara Berg, Vikas Singh, Zihang Meng","submitted_at":"2021-05-12T20:53:30Z","abstract_excerpt":"We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse trace segment. We propose two novel tasks: (1) predict a trace given an image and caption (i.e., visual grounding), and (2) predict a caption and a trace given only an image. Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded. We present a novel mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.05964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T20:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"4da8c183a65e3782d43d1f849baefa0d61796c07fccfc223696253284b2b66ca","abstract_canon_sha256":"b77e728dfbd7ee23b54d319b360cff60f13a141c77c066590703b6fcc57e7451"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:02.444306Z","signature_b64":"cC1eE+i6+SKNU1kKO/5b7ZXF//jshvPyNmAPj7EH+lbXWvtd+TUbkV7uzln4byyCWI3jvwG5q31QXJKpUFchAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0543618fb3780b3750fa38d273294001f567c07e430573e5e2c5b0f52fd9c1ba","last_reissued_at":"2026-07-05T02:40:02.443971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:02.443971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amy Bearman, Babak Damavandi, Licheng Yu, Ning Zhang, Tamara Berg, Vikas Singh, Zihang Meng","submitted_at":"2021-05-12T20:53:30Z","abstract_excerpt":"We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse trace segment. We propose two novel tasks: (1) predict a trace given an image and caption (i.e., visual grounding), and (2) predict a caption and a trace given only an image. Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded. We present a novel mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05964","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.05964/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.05964","created_at":"2026-07-05T02:40:02.444031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05964v1","created_at":"2026-07-05T02:40:02.444031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05964","created_at":"2026-07-05T02:40:02.444031+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVBWDD5TPAFT","created_at":"2026-07-05T02:40:02.444031+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVBWDD5TPAFTOUH2","created_at":"2026-07-05T02:40:02.444031+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVBWDD5T","created_at":"2026-07-05T02:40:02.444031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH","json":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH.json","graph_json":"https://pith.science/api/pith-number/AVBWDD5TPAFTOUH2HDJHGKKAAH/graph.json","events_json":"https://pith.science/api/pith-number/AVBWDD5TPAFTOUH2HDJHGKKAAH/events.json","paper":"https://pith.science/paper/AVBWDD5T"},"agent_actions":{"view_html":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH","download_json":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH.json","view_paper":"https://pith.science/paper/AVBWDD5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05964&json=true","fetch_graph":"https://pith.science/api/pith-number/AVBWDD5TPAFTOUH2HDJHGKKAAH/graph.json","fetch_events":"https://pith.science/api/pith-number/AVBWDD5TPAFTOUH2HDJHGKKAAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH/action/storage_attestation","attest_author":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH/action/author_attestation","sign_citation":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH/action/citation_signature","submit_replication":"https://pith.science/pith/AVBWDD5TPAFTOUH2HDJHGKKAAH/action/replication_record"}},"created_at":"2026-07-05T02:40:02.444031+00:00","updated_at":"2026-07-05T02:40:02.444031+00:00"}