{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TPWXXV6KEHKGZPJOFQ4MYSPAIH","short_pith_number":"pith:TPWXXV6K","schema_version":"1.0","canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","source":{"kind":"arxiv","id":"2405.20648","version":2},"attestation_state":"computed","paper":{"title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adithya Vasudev, Austin Peng, Richard Luo, Rishabh Jain","submitted_at":"2024-05-31T07:30:24Z","abstract_excerpt":"Video is an increasingly prominent and information-dense medium, yet it poses substantial challenges for language models. A typical video consists of a sequence of shorter segments, or shots, that collectively form a coherent narrative. Each shot is analogous to a word in a sentence where multiple data streams of information (such as visual and auditory data) must be processed simultaneously. Comprehension of the entire video requires not only understanding the visual-audio information of each shot but also requires that the model links the ideas between each shot to generate a larger, all-enc"},"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":"2405.20648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"abe8c6d234c8bffa15cac04657adc75bd67d4d9e580fd7da74be497f21cadac6","abstract_canon_sha256":"7fe560f641ebee39992ad7028d25bda566609d00f92dd2103dda292d6193a493"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:27.479822Z","signature_b64":"StiKvIQNSyY87YkxZ2maZK0cFQahZrHhS78OWZv2Lr17AV90iyJjU2u+Nb2Wv+K/pB6AuAziL9UaY7KtmjJ8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","last_reissued_at":"2026-07-05T09:26:27.479381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:27.479381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adithya Vasudev, Austin Peng, Richard Luo, Rishabh Jain","submitted_at":"2024-05-31T07:30:24Z","abstract_excerpt":"Video is an increasingly prominent and information-dense medium, yet it poses substantial challenges for language models. A typical video consists of a sequence of shorter segments, or shots, that collectively form a coherent narrative. Each shot is analogous to a word in a sentence where multiple data streams of information (such as visual and auditory data) must be processed simultaneously. Comprehension of the entire video requires not only understanding the visual-audio information of each shot but also requires that the model links the ideas between each shot to generate a larger, all-enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20648","kind":"arxiv","version":2},"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/2405.20648/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":"2405.20648","created_at":"2026-07-05T09:26:27.479437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20648v2","created_at":"2026-07-05T09:26:27.479437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20648","created_at":"2026-07-05T09:26:27.479437+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPWXXV6KEHKG","created_at":"2026-07-05T09:26:27.479437+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPWXXV6KEHKGZPJO","created_at":"2026-07-05T09:26:27.479437+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPWXXV6K","created_at":"2026-07-05T09:26:27.479437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21785","citing_title":"Comparing Learning Paradigms for Egocentric Video Summarization","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH","json":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH.json","graph_json":"https://pith.science/api/pith-number/TPWXXV6KEHKGZPJOFQ4MYSPAIH/graph.json","events_json":"https://pith.science/api/pith-number/TPWXXV6KEHKGZPJOFQ4MYSPAIH/events.json","paper":"https://pith.science/paper/TPWXXV6K"},"agent_actions":{"view_html":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH","download_json":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH.json","view_paper":"https://pith.science/paper/TPWXXV6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20648&json=true","fetch_graph":"https://pith.science/api/pith-number/TPWXXV6KEHKGZPJOFQ4MYSPAIH/graph.json","fetch_events":"https://pith.science/api/pith-number/TPWXXV6KEHKGZPJOFQ4MYSPAIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/action/storage_attestation","attest_author":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/action/author_attestation","sign_citation":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/action/citation_signature","submit_replication":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/action/replication_record"}},"created_at":"2026-07-05T09:26:27.479437+00:00","updated_at":"2026-07-05T09:26:27.479437+00:00"}