{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4SAMN2RP5VEFHXL45HEF45ZB6K","short_pith_number":"pith:4SAMN2RP","schema_version":"1.0","canonical_sha256":"e480c6ea2fed4853dd7ce9c85e7721f2b2949c19bd05f34c31faba3bdaf1765a","source":{"kind":"arxiv","id":"1807.01122","version":1},"attestation_state":"computed","paper":{"title":"Getting the subtext without the text: Scalable multimodal sentiment classification from visual and acoustic modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aparna Bharati, Daniel Moreira, Nathaniel Blanchard, Walter J. Scheirer","submitted_at":"2018-07-03T12:38:11Z","abstract_excerpt":"In the last decade, video blogs (vlogs) have become an extremely popular method through which people express sentiment. The ubiquitousness of these videos has increased the importance of multimodal fusion models, which incorporate video and audio features with traditional text features for automatic sentiment detection. Multimodal fusion offers a unique opportunity to build models that learn from the full depth of expression available to human viewers. In the detection of sentiment in these videos, acoustic and video features provide clarity to otherwise ambiguous transcripts. In this paper, w"},"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":"1807.01122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-03T12:38:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6740a5983e020853d7409f6f38792e3752d4c4cbb1562e671e648ae41a421327","abstract_canon_sha256":"666f311f01e7bee96eb811ba730b06925fdb8258922b1192add0b1c9bfb9deb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:45.249120Z","signature_b64":"Stuf/t4gKktNFNZNs4VThlgjN7S0AaVCerNt72amXje2LSDC+8VoBOFfPdbZMtJ418hcFv/13PQITrTLII16AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e480c6ea2fed4853dd7ce9c85e7721f2b2949c19bd05f34c31faba3bdaf1765a","last_reissued_at":"2026-05-18T00:11:45.248360Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:45.248360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Getting the subtext without the text: Scalable multimodal sentiment classification from visual and acoustic modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aparna Bharati, Daniel Moreira, Nathaniel Blanchard, Walter J. Scheirer","submitted_at":"2018-07-03T12:38:11Z","abstract_excerpt":"In the last decade, video blogs (vlogs) have become an extremely popular method through which people express sentiment. The ubiquitousness of these videos has increased the importance of multimodal fusion models, which incorporate video and audio features with traditional text features for automatic sentiment detection. Multimodal fusion offers a unique opportunity to build models that learn from the full depth of expression available to human viewers. In the detection of sentiment in these videos, acoustic and video features provide clarity to otherwise ambiguous transcripts. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01122","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.01122","created_at":"2026-05-18T00:11:45.248502+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01122v1","created_at":"2026-05-18T00:11:45.248502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01122","created_at":"2026-05-18T00:11:45.248502+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SAMN2RP5VEF","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SAMN2RP5VEFHXL4","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SAMN2RP","created_at":"2026-05-18T12:32:05.422762+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/4SAMN2RP5VEFHXL45HEF45ZB6K","json":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K.json","graph_json":"https://pith.science/api/pith-number/4SAMN2RP5VEFHXL45HEF45ZB6K/graph.json","events_json":"https://pith.science/api/pith-number/4SAMN2RP5VEFHXL45HEF45ZB6K/events.json","paper":"https://pith.science/paper/4SAMN2RP"},"agent_actions":{"view_html":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K","download_json":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K.json","view_paper":"https://pith.science/paper/4SAMN2RP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01122&json=true","fetch_graph":"https://pith.science/api/pith-number/4SAMN2RP5VEFHXL45HEF45ZB6K/graph.json","fetch_events":"https://pith.science/api/pith-number/4SAMN2RP5VEFHXL45HEF45ZB6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K/action/storage_attestation","attest_author":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K/action/author_attestation","sign_citation":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K/action/citation_signature","submit_replication":"https://pith.science/pith/4SAMN2RP5VEFHXL45HEF45ZB6K/action/replication_record"}},"created_at":"2026-05-18T00:11:45.248502+00:00","updated_at":"2026-05-18T00:11:45.248502+00:00"}